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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive, so the bar is lower and the safety profile is covered. The description adds real behavioral value beyond that: it discloses what the output contains (sources screened, unavailable-source notes, reviewer checklist) and the epistemic limit ('informational evidence organization, not legal advice or sanctions clearance'). No contradiction with annotations exists.

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?

Three sentences with zero waste: the main action is front-loaded, the composition details follow in the second sentence, and the caveat lands last. Each sentence earns its place and the ordering moves from what → contents → limitation.

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 multi-source tool with no output schema, the description carries the burden of explaining the result and largely succeeds: it lists the covered source domains, the output components (unavailable-source notes, reviewer checklist), and the scope limitation. It could go further on how a caller should interpret or act on the checklist, but for a read-only, idempotent aggregator the description is nearly complete.

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 description coverage is 100%, so per the baseline the schema already documents all six parameters. The description adds modest context by framing ein/lei/ticker as 'canonical identity and join keys' (i.e., optional resolution hints) and by tying 'one company' to the required company param, but it does not deepen parameter semantics meaningfully beyond that.

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: 'Assemble a reusable KYB/AML evidence case file for one company,' with a concrete scope boundary (single company). It enumerates the constituent parts (identity/join keys, GLEIF ownership-chain screening, sanctions/SEC/EPA/federal-awards standing) and explicitly distinguishes itself from related outputs via the 'not legal advice or sanctions clearance' caveat.

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 conveys clear context: this is the consolidated case-file assembler rather than a point screen, which implicitly routes an agent away from siblings like beneficial_owner_screen or corporate_ownership_tree. It offers a when-not exclusion ('not legal advice or sanctions clearance') but never names alternative tools or the conditions that would select them, so it stops short of full explicitness.

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