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

Annotations declare readOnlyHint=false and destructiveHint=false but leave the nature of the write opaque; the description fills that gap by clarifying this 'records a product signal' and does not perform the missing action. It also adds the non-obvious 'call this once only' constraint, useful context beyond the annotation set. Does not cover what the recorded signal yields or any confirmation behavior.

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?

Four short sentences, front-loaded with purpose and the when-to-use condition, then parameter guidance, then a final disambiguating statement. No filler or redundancy; every sentence carries distinct information.

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 non-idempotent write with no output schema and only 25% parameter coverage, the description provides enough to call it correctly: trigger condition, scope of input, and confirmation that no downstream action occurs. It could mention what happens after recording (e.g., who consumes the signal) but nothing essential for correct invocation is missing.

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 coverage is only 25% (just user_intent documented), so the description must compensate. It does: it maps user_request to 'describe the request', missing_capability to 'the smallest missing capability', and explains attempted_tools' expected format ('short comma-separated string') and conditionality ('if relevant'). Only user_intent is left to the schema, which handles it.

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 verb and resource — 'Report a user request that no Trakkr tool can satisfy' — and the scope condition (no tool can satisfy it) cleanly separates it from the many get_*/manage_* siblings that actually perform actions. The final clause 'it does not perform the missing action' further disambiguates it from the action-oriented tools.

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?

Explicitly states when to invoke ('Call this once only when the requested outcome is genuinely unavailable'), giving both a trigger and a frequency constraint. No sibling is named as an alternative, but the 'no Trakkr tool can satisfy' framing functions as an implicit exclusion against the entire catalog, which is reasonable for a meta/telemetry tool.

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