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

Annotations (readOnlyHint, openWorldHint, idempotentHint) cover safety, but the description adds rich behavioral context: it explains the cascade through multiple lookup endpoints, graceful degradation when GLEIF/OpenFIGI is unavailable, ambiguity handling via `figi_candidates`, and explicit `unresolved` lists. It also discloses that identifiers are sourced and labelled, adding transparency beyond what annotations provide.

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?

Though long, every sentence carries critical information. The description is front-loaded with the most important guidance ('Use FIRST...') and then systematically covers types, edge cases, and failure modes. It avoids redundancy and wastes no words; the length is justified by 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?

Given no output schema, the description exhaustively covers what the agent needs: accepted inputs, return values (identifiers, `unresolved`, `figi_candidates`), source labels, degradation behavior, and rationale for when it replaces manual lookups. It leaves no ambiguity about how to call the tool correctly or what to expect from the response.

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%, yet the description adds substantial semantic detail: it explains the meaning of `type` values, gives examples for `value` (ticker, CIK, name for company; brand/generic for drug), and crucially warns against passing trailing security-class words for bonds. It also clarifies that an ISIN resolves to the legal entity via GLEIF mapping, which is not evident from the schema alone.

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 specific verb ('resolve') and resource ('user-spoken NAME to canonical/official identifiers'). It distinguishes itself from siblings by explicitly saying 'Use FIRST whenever you have a name but need an ID' and lists the exact types of queries it handles (ticker, CIK, LEI, RxCUI). It also contrasts with the sibling 'compare_entities' implicitly, as it produces identifiers rather than comparisons.

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 context: 'Use FIRST whenever you have a name but need an ID.' It also clarifies when not to use it (e.g., when a name matches multiple instruments, it returns candidates rather than asserting, and it instructs the caller to pass only the entity name, not the full noun phrase). It differentiates between entity types and notes that non-equity instruments resolve here, which is a key decision point.

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