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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds substantial behavioral context beyond those: graceful degradation when GLEIF/OpenFIGI are unavailable, explicit reporting of unresolved identifiers, and the behavior of returning figi_candidates for ambiguous matches. It also notes the internal multi-endpoint cascade, which sets correct expectations about latency and logic. No contradiction with annotations.

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?

The description is long but highly structured, opening with examples and core purpose, then detailing supported types and edge cases. Every sentence contributes value—there is no filler. The length is justified given the tool's complexity, though a slightly tighter edit could trim redundancy without losing 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?

Despite having no output schema, the description fully explains what the tool returns: identifiers with source labels, an explicit unresolved list, and the figi_candidates structure for ambiguous cases. It also covers input handling, fallback behavior, and which sources are used for each type. Given the tool's complexity, the description is comprehensive enough that an agent can call it correctly without additional lookups.

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?

Although the schema covers both parameters at 100%, the description adds critical semantics beyond the schema. For the 'value' parameter, it clarifies that only the entity name should be passed, provides examples (AAPL, CIK, brand names), and warns against including trailing security-class words that would break matching. This goes well beyond the schema's simple description.

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 clearly states the verb 'resolve' and the resource 'entity'—turning a name into canonical identifiers. It provides multiple example queries and explicitly distinguishes itself with 'Use FIRST whenever you have a name but need an ID.' It also specifies the two supported types and the sources for each, making the purpose unambiguous and differentiated from siblings.

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 description gives explicit when-to-use: 'Use FIRST whenever you have a name but need an ID.' It provides detailed guidance on input format—emphasizing to pass only the entity name, with a concrete example of what to avoid ('never the question's full noun phrase'). It also explains when to use the 'drug' type and how to handle ambiguous matches, covering both success and failure scenarios.

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