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

Annotations already declare readOnlyHint/idempotentHint, and the description adds substantial behavior beyond them: ambiguity handling ("asserts nothing and returns figi_candidates"), graceful degradation ("if GLEIF or OpenFIGI is unavailable, the EDGAR identifiers still return"), explicit reporting of failures ("an identifier that could NOT be resolved is stated explicitly under `unresolved` rather than omitted"), source-labelled identifiers, and the internal cascade across endpoints. No contradiction with the read-only/idempotent annotations exists — the description is consistent with them.

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 definition is front-loaded with purpose and trigger examples, and nearly every sentence earns its place. However, it is a dense wall of prose: the "company" type is explained in a single ~200-word run-on sentence with deep parentheticals (FIGI candidates, bond behavior, ISIN mapping all nested inside), which makes parsing harder than necessary. Reformatting into bullets or shorter sentences would preserve all content while improving readability.

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 return-value burden, and it largely delivers: it names response elements (figi_candidates for ambiguous matches, `unresolved` for failures, source labels, drug result shape of RxCUI + ingredient + brand + pipeworx citation). For a two-type, multi-endpoint resolver this is thorough. Minor gaps: no concrete example response object, and the drug path is given much less depth than the company path.

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 description coverage is 100%, so the baseline is 3, and the schema's `value` description is already exemplary. The description adds meaning beyond it: ISIN as a fourth accepted input form (the schema lists only ticker, CIK, or name), the ISIN-to-LEI legal-entity resolution for non-US issuers, and the enrichment-degradation behavior that affects what the returned identifiers mean. It also expands the `type` enum values with concrete output semantics (CIK+ticker+LEI+FIGI vs. RxCUI+ingredient+brand).

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 natural-language triggers ("What's the ticker for…", "find the CIK for…") and then states a crisp verb+resource contract: "resolve a user-spoken NAME to the canonical/official identifiers other tools require as input." It enumerates two supported types (company, drug) with distinct output summaries, and differentiates itself from the sibling set by claiming "Use FIRST whenever you have a name but need an ID," which separates it from research-oriented tools like entity_profile and compare_entities.

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 an explicit trigger condition — "Use FIRST whenever you have a name but need an ID" — and even states what it replaces ("replaces 2-3 manual lookups"). The input-format rule ("Pass the ENTITY NAME ONLY… never the question's full noun phrase") is highly actionable guidance. However, it never names sibling alternatives or provides when-not-to-use conditions, so it stops short of full exclusion guidance.

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