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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive, so the description is not repeating those. It adds valuable behavioral context: the tool cascades through multiple lookup endpoints, explicitly lists unresolved identifiers under `unresolved` rather than omitting them, handles ambiguous matches with `figi_candidates`, and degrades gracefully if GLEIF/OpenFIGI are unavailable while still returning EDGAR data. No contradiction with annotations exists.

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 not wasteful—every clause carries operational weight (source coverage, ambiguity handling, fallback behavior). It is front-loaded with the purpose and the key 'Use FIRST' directive, then expands systematically. A 4 reflects that it is appropriately sized for a complex tool, though a tighter version could trim some redundancy without losing essential detail.

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 fully equips the agent: it explains input semantics, expected outputs (identifiers, unresolved field, figi_candidates), multi-source behavior, ambiguity handling, and graceful degradation. It also notes that using it replaces 2-3 manual lookups, setting expectations on cost/performance. Nothing an agent needs to call it correctly 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?

While the schema describes both parameters, the description adds crucial meaning beyond the schema. For `type`, it details what each enum value resolves (company: CIK/ticker/LEI/FIGI with ownership; drug: RxCUI/ingredient/brand). For `value`, it clarifies that the input must be the exact issuer name for bonds, not the full noun phrase, and warns about trailing security-class words breaking FIGI lookup. This is exactly the kind of semantic guidance agents need.

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 phrasings that trigger the tool and states the core function: 'resolve a user-spoken NAME to the canonical/official identifiers other tools require as input.' It explicitly names the two supported types (company, drug) and what each returns, and differentiates from sibling tools by saying 'Use FIRST whenever you have a name but need an ID.' This is a specific verb+resource with clear differentiation from the many sibling research tools.

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 when-to-use rule ('Use FIRST whenever you have a name but need an ID.') and explains when it does NOT assert a single answer (ambiguous bond issuer returns figi_candidates instead, which is 'the correct answer'). It also instructs on input format ('Pass the ENTITY NAME ONLY') and notes graceful degradation. This goes beyond implied usage to concrete, actionable routing.

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