Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety bar is partly covered. The description adds the response shape and the hand-over-to-human behavior, plus the 'Advice only' scope limiter, but is silent on side effects (e.g., episode creation/logging) implied by readOnlyHint=false and on authentication needs.

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, front-loaded with the trigger condition, then the output, then a one-line scope limiter. Nothing is wasted and the most decision-relevant information comes first.

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?

Describing the return contents is valuable given there is no output schema, and hand-over behavior is disclosed. But for a 12-parameter tool with nested objects and thin annotation coverage, the description omits auth (api_key), episode grouping semantics, and how the many optional inputs shape the answer.

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?

Twelve parameters with only 50% schema description coverage, and the description names no parameter at all — not even the required task_summary or attempts. With half the inputs undocumented across both fields, the description does not compensate for the coverage gap.

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 action and trigger ('get a second opinion when you are stuck') and enumerates the return payload (diagnosis, checks, up to five recovery steps, hand-over criteria). However, it never distinguishes itself from close siblings like diagnose_loop, recommend_recovery, or assess_escalation, whose territory it appears to span.

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?

It gives clear triggers — stuck, retrying, uncertain, unable to make progress — which map well to concrete agent states. It stops short of exclusions or naming alternatives, so an agent deciding between this and diagnose_loop/recommend_recovery gets no routing help.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.