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

The annotations already mark the call as read-only, open-world, and idempotent, and the description adds substantial behavioral detail beyond those flags: graceful degradation if GLEIF/OpenFIGI are unavailable, explicit `unresolved` output rather than silent omission, candidate-based behavior for ambiguous instruments, and internal cascading across multiple lookup endpoints. It accurately discloses edge-case behavior an agent would otherwise not infer.

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 and dense, but the length is justified by the complexity of multi-source identifier resolution. It is front-loaded with the core purpose and usage trigger, then uses clear section labels (SUPPORTED TYPES, LEI/FIGI enrichment, cascading behavior). Some parenthetical density could be tightened, but every substantive block earns its place.

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?

Despite having no output schema, the description explains what callers will receive: source-labelled identifiers, `figi_candidates` for ambiguous matches, `unresolved` entries for missing identifiers, and the RxCUI citation format. It also covers supported input formats, resolution strategy, and failure modes, so an agent has the context needed to invoke and interpret the tool 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?

Even with 100% schema coverage, the description materially enriches parameter semantics: it clarifies that `value` should be the ENTITY NAME ONLY, gives examples of correct vs. incorrect inputs for bonds, and explains how ISINs map to legal entities. The `type` parameter benefits from the detailed company/drug behavior descriptions, going well beyond the enum labels in the schema.

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 precise purpose: resolving a user-spoken NAME into canonical identifiers (CIK, ticker, LEI, RxCUI, FIGI) that other tools require. The opening example queries and explicit "Use FIRST whenever you have a name but need an ID" make the tool's role unmistakable and distinguish it from siblings like entity_profile, which would provide broader profile data rather than ID resolution.

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 provides clear when-to-use guidance: "Use FIRST whenever you have a name but need an ID," supported by representative user queries and the SUPPORTED TYPES breakdown. It stops short of naming alternative tools to use when this tool is not appropriate, but the trigger conditions and coverage limits are explicit enough for an agent to select it correctly.

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