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

Annotations declare read-only, idempotent, and open-world hints, and the description goes far beyond them: it discloses graceful degradation ('if GLEIF or OpenFIGI is unavailable, the EDGAR identifiers still return'), ambiguity handling ('when a name matches more than one instrument it asserts nothing'), and output labeling ('every identifier is labelled with the source that established it'). It also reveals the internal cascade ('replaces 2-3 manual lookups'), which is useful behavioral context. 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 dense and long, but every sentence earns its place given the tool's complexity (two entity types, multiple identifier systems, ambiguity rules, failure modes). It is front-loaded with purpose and the 'Use FIRST' directive before diving into details. Some cleanup is possible—parenthetical asides run long and bullet points would improve scanability—but the structure is logical and the length is justified.

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?

With no output schema, the description carries the full burden of explaining return values, and it does: it lists what is returned for each type, how unresolved identifiers are represented ('stated explicitly under `unresolved`'), and what happens on ambiguous matches. It also covers failure behavior, accepted input forms, and internal cascading. An agent has everything needed to invoke this correctly.

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 coverage is 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema. It explains what 'value' should be in context ('For a bond that is the ISSUER exactly as printed'), gives concrete examples ('AAPL', 'ozempic'), and clarifies why trailing security-class words fail ('the FIGI lookup matches instrument names'). This is exactly the kind of parameter enrichment that prevents mis-invocation.

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 clear, specific verb and resource: 'resolve a user-spoken NAME to the canonical/official identifiers other tools require as input.' It enumerates supported types (company, drug) with concrete identifier outputs (CIK, ticker, LEI, FIGI, RxCUI), and the example queries make the purpose instantly recognizable. It also differentiates from siblings by positioning itself as the 'first' step when an ID is needed, which separates it from entity_profile or ask_pipeworx.

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?

Explicit guidance is given: 'Use FIRST whenever you have a name but need an ID.' The description also explains when NOT to use it indirectly (ambiguous matches return figi_candidates rather than asserting), and provides critical input-formatting rules ('Pass the ENTITY NAME ONLY... never the question's full noun phrase'). This is clear, actionable routing that leaves little to inference.

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