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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: the prior rating is replaced, the result is visible to teammates, and it feeds the ICP's fit insights. It also explains the idempotency contract concretely ('retrying with the same idempotencyKey and input returns the first result instead of repeating the action'), which is more useful than the bare hint. Still silent on permissions/authorization and what the call returns.

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?

Two sentences, front-loaded with the action and its outcomes, then the side effects and idempotency rule. Every clause carries information (rating semantics, replacement, visibility, downstream evidence, retry behavior) with no filler.

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 destructive, nested-schema mutation with no output schema, the description covers the important behavioral surface: what gets overwritten, who sees it, what it feeds, and how retries behave. The remaining gap is the cardId/entity_id parameter relationship and any permission requirements, which the schema does not resolve on its own.

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 reported at 33% and only cardId lacks an inline description, but the description itself adds little parameter-level detail beyond restating that reason and note are optional and that neutral discards them. It notably does not clarify the relationship between params.cardId and body.entity_id, two required UUIDs on a nested object, which is the most likely source of caller error.

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 opens with a specific verb and resource ('Records whether a pipeline company or one of its contacts is a good fit'), and names all three outcome values (like/dislike/neutral) plus the clear-on-neutral behavior. The write semantics are unambiguous against read siblings such as listCompanyFitRatings, though no sibling is named 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?

Usage is implied rather than stated: the agent learns this is the tool for recording a fit judgment, and that a cleared rating is expressed via rating=neutral. There is no explicit 'use this instead of X' routing, no mention of preconditions (e.g. needing the company already in the pipeline), and no guidance on when to prefer updating an existing rating versus leaving it alone.

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