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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial behavior beyond that: graceful degradation ("if GLEIF or OpenFIGI is unavailable, the EDGAR identifiers still return"), ambiguity handling ("when a name matches more than one instrument it asserts nothing and returns figi_candidates"), explicit unresolved reporting ("stated explicitly under unresolved rather than omitted"), and internal endpoint cascading. No contradiction 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 well — triggering queries and the "Use FIRST" rule appear immediately — and nearly every sentence carries useful information. However, it is a single dense run-on paragraph with deeply nested parentheticals (the company-type explanation buries key facts like figi_candidates and unresolved inside long clauses), which makes key extraction harder than it should be for an agent.

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, two-type tool with no output schema, the description covers inputs, outputs per type, failure modes, ambiguity, and degradation remarkably well. Remaining gaps: the drug type receives comparatively thin treatment (no ambiguity or resolution-failure detail) and the overall return shape is never described, but these are minor given the depth already present.

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% and the schema already supplies examples (AAPL, 0000320193, "ozempic") plus the entity-name-only caution for bonds. The description goes beyond the schema by adding ISIN as an accepted input form, explaining the GLEIF ISIN-to-LEI mapping for non-US issuers, and clarifying that non-equity instruments without tickers still resolve — genuinely new parameter meaning beyond baseline.

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 and resource: "resolve a user-spoken NAME to the canonical/official identifiers other tools require as input." It enumerates concrete triggering queries ("What's the ticker for…" / "find the CIK for…") and the two supported types with their outputs, distinguishing itself from siblings like entity_profile and compare_entities which presume an ID or entity, not a name-to-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?

Provides an explicit when-to-use rule: "Use FIRST whenever you have a name but need an ID," plus an efficiency argument ("using resolve_entity replaces 2-3 manual lookups"). It does not name a specific sibling alternative or state exclusion conditions (e.g., what to use when you already hold an ID), so some routing inference is left to the agent.

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