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

Annotations provide only read-only, open-world, and idempotent hints. The description goes far beyond that: it discloses internal cascading lookups, graceful degradation when GLEIF/OpenFIGI are unavailable, explicit `unresolved` fields, source-labelled identifiers, ambiguity handling via `figi_candidates`, and behavior for non-equity instruments. This is a strong behavioral disclosure.

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 information-dense and front-loaded with example query phrases, but it is a long, unwieldy single block of text with many nested parentheticals. Every sentence carries useful content, yet structure is sacrificed: scannability would improve dramatically with bullets or clear separation of types, inputs, and return behavior.

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 and moderate parameter count, the description is very complete: it covers accepted inputs, return identifiers, source attribution, unresolved results, ambiguity policy, degradation behavior, supported entity types, and even non-US issuer coverage. An agent has enough grounding to select and invoke the tool correctly across a wide range of queries.

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 the schema carries the baseline parameter documentation. The description adds meaningful context: accepted input forms (ticker, CIK, ISIN, name for company; brand/generic for drug), the requirement to pass only the entity name rather than the full noun phrase, and how ISIN inputs resolve to legal entities. This enriches rather than merely repeats 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 specific action — resolving a user-spoken name to canonical/official identifiers — and names concrete outputs (CIK, ticker, LEI, FIGI, RxCUI). It clearly differentiates the tool from siblings like entity_profile or search_within by explicitly saying to use it when you have a name but need an ID.

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 explicitly says 'Use FIRST whenever you have a name but need an ID', enumerates supported entity types, and explains behavior when resolution is ambiguous. It does not explicitly name alternative sibling tools or state when not to use it, so it falls just short of full 5.

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