get_warningsRetrieve warnings for AI models flagged as unreliable or needing caution on a specific task like inbox triage, meeting scheduling, or receipts.
Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task id, e.g. 'receipts'. See list_tasks. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful substance about what the warnings represent (the flag categories) but says nothing about return shape, whether results can be empty, or how warnings relate to get_scores output.
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?
A single tight sentence with no filler; the parenthetical examples earn their place by concretizing the flag types. Phrasing is slightly compressed ('Models RealRun flagged') but front-loads the object of the call.
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?
For a one-parameter, fully documented read-only lookup with no output schema, the description tells the agent what the tool returns in enough detail to call it. The missing piece is how these warnings should feed into model selection relative to get_scores.
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?
Schema description coverage is 100% and the single 'task' parameter is a documented enum pointing at list_tasks, so the schema carries the burden. The description adds no parameter-level meaning beyond that, making the baseline 3 appropriate.
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?
The description states a specific resource and filter: models flagged as 'not recommended' or 'needing caution' for a given task, plus concrete example categories (scam failures, invented data, inconsistency). It is clearly distinguishable from get_scores by virtue of returning safety flags rather than numeric ratings, though it never names that sibling explicitly.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named despite get_scores and recommend_model being obvious siblings. The agent must infer from context that this is a pre-recommendation safety check.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.