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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the description is free to add the important non-mechanical context: answers do not establish eligibility, verified evidence, savings, owner authority, payment, or filing readiness. The privacy constraint (no exact income, ages, identifiers, documents, or caller-supplied audit) is a genuinely useful behavioral rule found nowhere in the structured fields.

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 compact sentences front-load the action, then the output nature, then the input restrictions. The long disclaimer clause is dense but each piece carries a distinct constraint; only the enumeration of disclaimed outcomes could be trimmed slightly.

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 read-only screening tool with no output schema, the description adequately conveys what comes back (research and questions) and what it does not guarantee. However, it leaves the caller guessing about the nested owner_answers payload and the optional county_key, which is the main thing an agent needs to construct a valid call.

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?

With only 33% schema description coverage and a large nested owner_answers object, the description does little more than gesture at 'a few owner-reported categories' and forbid sending exact income/ages/identifiers. It never explains how the many boolean requirement fields (freeze_age_requirement_met, veteran_disability_requirement_met, etc.) or county_key should be supplied, so the coverage gap is only partially compensated.

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+resource: recheck possible tax-reduction routes against retained property records plus owner-reported categories, and clarifies the deliverable is 'research and next questions' rather than an audit. It implicitly distinguishes itself from the many audit_* siblings by disclaiming verification, though it never names an alternative 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?

'Recheck' implies a prior pass, and the returned-research framing hints at preliminary screening versus full auditing, but the description never says when to pick this over audit_property_tax or similar siblings. The prohibition on a 'caller-supplied audit' is the only explicit routing signal, and it is negative-only.

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