Retrospective archive of shutdown-risk scores joined to recorded outcomes. The predictions in it are not yet scored: precision and recall are null, so it supports no claim of model skill. Read its evaluation limits in the response.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the read-only, closed-world safety profile, and the description adds genuinely non-obvious context: the predictions are unscored, precision and recall are null, and evaluation limits are embedded in the response. That is real disclosure an agent could not get from annotations. It stops short of describing what the joined archive actually contains row-by-row.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences with no filler, and the key caveat (unscored predictions, null precision/recall) is placed before the pointer to the response's evaluation limits. Slightly repetitive in restating the 'no model skill' point twice.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description carries the burden of explaining returns; it only gestures at 'evaluation limits' without saying what fields the archive exposes (score, outcome, null metrics). For a no-argument archival tool this is adequate but leaves the agent guessing about payload shape.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool is 4. The schema coverage is also 100%, so no compensating detail is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific resource and framing: a 'retrospective archive of shutdown-risk scores joined to recorded outcomes', which tells an agent this is an outcome-joined historical dataset rather than a live risk score. It never names its obvious siblings (get_shutdown_risk, get_shutdown_risk_leaderboard), so the distinction is inferable but not explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied rather than stated: the archive is for accountability against recorded outcomes, and the warning that it 'supports no claim of model skill' implies it should not be used for validation claims. There is no explicit when-to-use or when-to-prefer-get_shutdown_risk guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.