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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, lowering the bar. The description adds valuable behavioral detail: ambiguous names return `figi_candidates` instead of asserting; unresolved identifiers are explicitly listed under `unresolved`; LEI/FIGI enrichment degrades gracefully when sources are down; and it returns a citation URI for drug lookups. No contradictions 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 front-loaded with query examples and the 'Use FIRST' directive, so the most important usage guidance appears early. The company-type parenthetical is a dense run-on sentence, but every clause carries crucial behavioral information (ambiguity handling, unresolved field, source labeling, ISIN-to-LEI mapping). It is verbose but justifiably so given the tool's complexity.

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 bears the burden of explaining return values, and it does: it mentions return of `figi_candidates`, `unresolved`, identifier-source labels, and for drugs lists RxCUI + ingredient + brand + citation. It covers all input types, edge cases (multiple matches, unavailable sources), and the internal cascade of lookups. Nothing essential for correct invocation is missing.

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 baseline is 3, but the description adds critical semantics beyond the schema. For `value` it warns 'Pass the ENTITY NAME ONLY' and gives a detailed example about bond issuer names versus full noun phrases, explaining why trailing security-class words match nothing. For `type`, it enumerates what each enum value returns (CIK, ticker, LEI, FIGI, RxCUI, ingredient, brand). This significantly enhances agent understanding.

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 a barrage of user-phrased queries ('What's the ticker for…', 'find the CIK for…') and then states the verb precisely: 'resolve a user-spoken NAME to the canonical/official identifiers other tools require as input.' This clearly distinguishes the tool from siblings like entity_profile or compare_entities, which focus on profile or comparison rather than name-to-ID resolution. The 'Use FIRST' directive and mention of replacing 2-3 manual lookups further cement its unique role.

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?

It explicitly says 'Use FIRST whenever you have a name but need an ID', which is a strong directive that applies before considering alternatives. It also gives concrete query examples and explains scope boundaries (e.g., covers non-US issuers EDGAR cannot reach). It does not name specific alternative tools or give explicit 'do not use when' conditions, so it misses the full 5, but the context is clear.

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