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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a confidence score is attached to results, output is a per-source summary plus top records, and matches are name-based so identity must be verified before relying on any link — a material false-positive caveat. It stops short of describing confidence-score semantics or failure behavior when a source has no match.

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?

Front-loaded with the core purpose, then sources, then return shape, then the matching caveat — a sensible ordering. The 'single AI-native lookup across data that otherwise lives in separate silos' sentence partially restates the earlier 'consolidated cross-source' framing, so there is mild redundancy, but nothing is padded.

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?

With no output schema, the description carries the return-value burden and does so at a high level: per-source summary plus top records, with a confidence score. Sources and the name-matching caveat are covered. It is slightly thin on how the confidence score is derived and what a per-source summary contains, but an agent has enough to invoke and interpret it.

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%: name, limit (default 5, max 15), and state are all documented in the schema with examples and bounds. The description adds no parameter-level detail (it never mentions the limit or state knobs), so it neither compensates nor is needed to — baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb (build) and resource (consolidated cross-source dossier) and enumerates exactly which sources are aggregated: EDGAR registration, EPA ECHO environmental/facility data, and OFAC/UN/EU/BIS sanctions screening. This clearly distinguishes it from single-source siblings like edgar_company_lookup, epa_facility_search, or sanctions_screen_entity, and from adjacent dossier tools such as issuer_diligence_dossier.

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?

'Build ... in one call' and 'a single AI-native lookup across data that otherwise lives in separate silos' implies the selection condition: use this instead of calling the individual silo tools when you need a consolidated view. However, it never states an explicit when-not (e.g., use the single-source tools when you only need EDGAR or only need screening), so the routing guidance is implied rather than spelled out.

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