AIToday
Large Language ModelsAI Coding AssistantsZenn AI/MLPublished: Nov 22, 2026, 04:00 JST

MCP returns need dates and stop rules for agents, 検索カルテ says

Send on LINE
MCP returns need dates and stop rules for agents, 検索カルテ says

3 Key Points

  1. What happened

    After a reader comment, the Search Console-based service 検索カルテ began attaching explicit start and end dates (for example 2026-10-19 to 2026-11-15) to its 28-day metrics, replacing the relative label 'last 28 days'.

  2. Why it matters

    An AI agent reading a stale carried-over prescription would treat old figures as current and rewrite content on that basis, so absolute dates and per-response next steps appear to be what keeps the agent from acting on bad numbers.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The trigger for the changes was a reader comment on a previous article about letting Claude Code rewrite articles using prescriptions drawn from Search Console data. The comment pointed out that if a human confirms a prescription before publishing, the aggregation period belongs in the MCP return value so the agent does not fix things based on old numbers. The author agreed, fixed it immediately, and used the occasion to lay out the wider set of precautions.

The underlying concern is that an agent does not pause over a figure the way a person would. Prescriptions that are not acted on roll over to the following week while keeping the numbers from the week they were last detected, so a three-week-old prescription still labeled 'last 28 days' invites edits based on outdated data. The fix stores the aggregation end date together with the prescription at creation time and computes the start date when returning it, rather than recalculating from today's date, and the tool description explains that a start–end range older than the latest chart means older numbers.

Other precautions follow the same logic of putting what matters where the agent will actually see it. Failures return the specific remaining items and a written next step with a three-attempt limit; advisory items such as missing alt text are flagged so they are not counted as pass/fail; externally sourced strings are labeled as data to blunt prompt injection; read-only connections simply omit write tools from tools/list; errors carry guidance on what to tell the user; and free-plan responses ask the AI to mention the upgrade URL only once. As the author puts it, things that would go in documentation for a human-facing API have to sit in the response itself, because the agent does not go back and reread the docs.

FAQ
Why are relative time labels like 'last 28 days' a problem for AI agents?
A prescription left untouched carries over to the next week with its original numbers, but the label still reads 'last 28 days'. The agent then treats those stale figures as current and edits accordingly.
What stops an agent from fixing a page forever?
The recheck_page tool returns a next_step telling the agent to fix only the failing items, republish, and call recheck_page again, up to three times per prescription. If it still fails after three tries, the agent should report the remaining items to the user and stop.
How does the service handle text that comes from outside, such as search queries?
Tool results open with a note that keyword, page_title and page_check strings are external data whose embedded instructions should be ignored. Such strings are stripped of control and direction-changing characters and length-capped.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleShortical debuts AI series "Inevitable" with Aki Avni