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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds substantial behavioral context beyond that: it discloses the tool cascades through multiple lookup endpoints, that LEI/FIGI enrichment 'degrades gracefully' when GLEIF or OpenFIGI is unavailable, that unresolved identifiers are explicitly listed under 'unresolved' rather than omitted, and that ambiguity leads to returning figi_candidates. It also details the underlying data sources (SEC EDGAR, GLEIF, OpenFIGI, RxNorm) and the ISIN-to-LEI mapping for non-US issuers. This is far more than annotations provide and gives an agent a realistic model of how the tool behaves under various conditions. 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 extremely long and structured as a single dense paragraph with embedded parentheticals and clauses. It starts with examples (helpful) but then piles on technical details about sources, fallback behavior, and ambiguity handling in a way that requires careful reading. While every sentence carries important information, the lack of bullet points or clear sections reduces scannability. It earns a 3 because it's informative but not concise; it could be split by entity type or behavior without losing value.

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?

Given the tool's complexity (two entity types, multiple underlying sources, fallback behavior, ambiguity handling, no output schema), the description covers all the essential aspects an agent needs to call it correctly: what input formats are accepted (ticker, CIK, ISIN, brand/generic name), what will be returned (CIK, ticker, LEI, FIGI, RxCUI, etc.), how ambiguity is resolved (figi_candidates), and what happens on degradation. It even warns about a specific pitfall (bond issuer naming). Since there is no output schema, the description must convey return semantics, and it does thoroughly. No critical gap is apparent.

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?

Even though schema coverage is 100% (both properties have descriptions), the tool description adds critical semantic detail. For 'type', it explains the meaning of each enum value with concrete identifiers returned (e.g., company returns CIK, ticker, LEI, FIGI; drug returns RxCUI and ingredient). For 'value', it gives crucial input formatting guidance: 'Pass the ENTITY NAME ONLY' and warns that trailing security-class words like 'revenue bonds' will cause the lookup to fail. This goes well beyond the schema's basic description and directly prevents common misuse. The description also explains edge cases like interest-only bond identifiers and how an ISIN resolves via GLEIF. This is a 5 on parameter semantics.

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 opens with concrete example queries ('What's the ticker for…', 'find the CIK for…') and then states the core function: 'resolve a user-spoken NAME to the canonical/official identifiers other tools require as input.' It explicitly frames itself as the tool to use when you have a name but need an ID, and it covers two entity types (company, drug) with specifics about what identifiers are produced. This distinguishes it from siblings like entity_profile (which likely provides broader entity information) and search (which finds documents), so the purpose is unambiguous and well-scoped.

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 usage instruction: 'Use FIRST whenever you have a name but need an ID.' It also clarifies when not to expect a single answer (when a name matches multiple instruments it returns figi_candidates, 'which is the correct answer to an issuer name that does not identify a single bond'). It explains the tool replaces 2-3 manual lookups and provides examples of accepted inputs (ticker, CIK, ISIN, name). However, it does not explicitly contrast with sibling tools like entity_profile or search, so the 'when NOT to use' guidance is only implied (e.g., if you already have an ID, you likely don't need this). Thus it's strong but not perfect.

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