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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description still adds meaningful behavior beyond them: it discloses that results are limited to previously publishable fact IDs, that the tool may abstain rather than answer, and that it carries formula scope, document version and evidence IDs. Abstention behavior is exactly the kind of trait annotations cannot express.

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-loaded with the read-only documentary framing before the return and exclusion clauses. Some density in 'public, read-only documentary example' and the source URL at the end, 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?

No output schema exists, so the description must carry return semantics, and it does — fact IDs, formula scope, document version, evidence IDs, or abstention. For a zero-parameter, annotated read-only tool this is nearly complete; only result-count or format limits are unaddressed, and those may not apply here.

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?

The input schema has zero parameters and full schema description coverage, so there is nothing for the description to disambiguate. Baseline for a parameterless tool applies; the description correctly implies a fully fixed, argument-free query rather than leaving the calling convention unclear.

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: searching archival home-insurance documents for leaks versus repair of the pipe. It also frames the tool as a 'documentary example,' which distinguishes it from live-data siblings like resolve_quote_intent. The phrasing 'leaks versus repair' is slightly compressed, but an agent can tell what it retrieves.

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?

Clearly delimits scope with explicit exclusions — 'never confirms current availability, personalized coverage, ranking or price' — which tells the agent when not to use it. What's missing is a positive pointer to the alternative tool for live availability or pricing, so the routing is implied rather than explicit.

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