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

Annotations (readOnlyHint, idempotentHint, destructiveHint) already cover safety, but the description adds substantial behavioral detail: it cascades through multiple internal endpoints, degrades gracefully when GLEIF/OpenFIGI are unavailable, explicitly lists unresolved identifiers under 'unresolved', and returns 'figi_candidates' when ambiguity exists. It also explains that non-equity instruments resolve here. This is far beyond what annotations provide.

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 extremely information-dense. It front-loads the purpose and usage directive, then organizes details under SUPPORTED TYPES with sub-sections. Every sentence adds value (e.g., the ISIN-to-LEI mapping, the non-equity note). It could be slightly more concise, but given the tool's complexity and the need to convey numerous edge cases, the verbosity is justified and well-structured.

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 complex tool with no output schema, the description is remarkably complete. It explains what identifiers are returned, how they are labeled, how ambiguity is handled (figi_candidates vs asserting nothing), what happens when sources are unavailable, and gives explicit input formatting rules. Even the internal cascade behavior is disclosed. An agent has everything needed to call this tool 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?

Schema schema coverage is 100% (both parameters described), but the description enriches meaning significantly: it explains that type accepts ticker/CIK/ISIN/name for company, gives examples (AAPL, 0000320193), and explicitly instructs to pass only the entity name, not the full noun phrase, with a concrete example. For drugs it clarifies brand vs generic. This goes well beyond the schema's basic descriptions.

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 states a specific verb ('resolve'), a resource ('canonical/official identifiers'), and enumerates the supported types (company, drug) with detailed sub-explanations. It clearly distinguishes itself from siblings by positioning it as the FIRST step when a name needs an ID, and by naming the specific identifier standards (CIK, ticker, LEI, FIGI, RxCUI). It also contrasts with alternatives like compare_entities or entity_profile, which are not mentioned but the purpose is unambiguous.

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?

Explicitly says 'Use FIRST whenever you have a name but need an ID.' It provides concrete examples of what to pass (ticker, CIK, ISIN, name for company; brand/generic for drug) and warns against pitfalls (e.g., not passing the full noun phrase for bonds). It also mentions graceful degradation for LEI/FIGI enrichment, implying when results may be partial. While it doesn't name direct alternatives, the 'first step' directive gives clear timing guidance.

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