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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add what they cannot: the result vocabulary, the fact that each verdict is accompanied by the source sentence it is based on, the determinism guarantee, and the instruction to elicit signals from the person rather than infer them. That is substantive behavior beyond the annotations, though it does not describe error handling for malformed or partial signal sets.

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 sentences, front-loaded with the core definition and the return vocabulary, with the elicitation rule placed last where it acts as an instruction. No filler. The clause 'each with the sentence from the site it is based on' is slightly awkward, but nothing is redundant.

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?

An output schema exists, so the description's recap of the verdicts is a bonus rather than a necessity, and the annotations cover the safety profile. The remaining shortfall is the nine nested booleans with no descriptions anywhere: an agent can see the names but not what a true or false means for criteria like 'only_independent_benchmark' or 'wants_to_buy_model_or_platform'.

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 0% and there are nine nested boolean signals whose names carry all the meaning, so the description has to compensate. It does partially: it establishes that all nine are yes/no, that they come from a published article on FDE fit, and that they must be asked of the person rather than guessed. It does not explain what any individual signal means, which is the gap the schema leaves.

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 names a specific verb and resource: a 'deterministic fit check with nine yes/no signals' and enumerates the five possible verdicts (fits, start_with_mapping, not_clear_yet, wait, something_else_fits_better). That is far more concrete than a title restatement. It does not explicitly differentiate itself from siblings such as run_readiness_scan or estimate_engagement, so it stops short of a 5.

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?

The line 'Ask the person; do not guess the signals' gives real operational guidance about how to source the inputs, and the mention that it flags when another kind of supplier is simpler implies a pre-engagement triage use. However, there is no explicit statement of when to call this versus estimate_engagement or run_readiness_scan, and no stated prerequisites or when-not conditions.

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