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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses substantial behavioral detail: it cascades through multiple lookup endpoints internally, degrades gracefully (returns EDGAR identifiers even if GLEIF/OpenFIGI are down), labels each identifier with its source, explicitly lists unresolved identifiers under `unresolved`, and explains the FIGI matching nuance (non-equity instruments resolve, but ambiguous names return candidates). This far exceeds what annotations convey and gives the agent a clear mental model of what to expect.

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 every sentence adds value. It is front-loaded with examples and the 'Use FIRST' directive, then progressively details supported types, fallback behavior, and parameter nuances. While not concise in a word-count sense, it is well-organized and earns its length given the multi-source complexity. The structure could be slightly tightened (e.g., separating the huge run-on sentence about company type), but it is not bloated with filler.

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 the tool's complexity (two entity types, multiple identifier sources, fallback behavior, ambiguity handling) and the absence of an output schema, the description does an excellent job of covering what an agent needs to know. It explains return behavior (figi_candidates, unresolved list, source labels), edge cases (bonds without tickers, ISIN-to-LEI mapping, foreign issuers), and input constraints. Nothing critical for correct invocation 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?

Schema coverage is 100% (both parameters documented), so baseline is 3. However, the description adds substantial meaning: it explains the `type` enum options in practical terms (the 'company' type covers CIK, ticker, name, and even ISIN mapping to legal entity), and for `value` it provides detailed guidance about passing only the entity name, warns against trailing security-class words, and gives examples. This goes well beyond the schema and directly improves correct invocation.

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 clearly states the verb (resolve) and the resource (user-spoken names to official identifiers). It lists concrete examples (ticker, CIK, LEI, RxCUI) and explicitly says 'Use FIRST whenever you have a name but need an ID,' which distinguishes it from siblings that likely operate on already-resolved entities. It leaves no doubt about what the tool does and when it is the right choice.

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 guidance: 'Use FIRST whenever you have a name but need an ID.' It also explains what happens in ambiguous cases (asserts nothing, returns figi_candidates) and how ISIN inputs are handled. It does not name specific sibling tools to avoid, but the 'Use FIRST' directive and the fact it replaces 2-3 manual lookups make the intended context clear. It could have been stronger by explicitly saying when NOT to use it, but the guidance is solid.

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