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

With no annotations, the description carries the full burden and does so well: it discloses that LEIs are compared as supplied and not validated against GLEIF, that Companies House corroboration is optional and external, and that the output is a verdict plus heuristic confidence and signal provenance. It omits whether the optional external lookup carries latency/quota costs or failure behavior.

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?

Four tight sentences, front-loaded with the core action, then the caveat, then the return shape. No filler and nothing that could be cut without losing information.

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 2-param tool with nested objects and no output schema, the description covers the method, the optional external dependency, the validation caveat, and the return shape (verdict, confidence, provenance). Minor gaps remain around degraded cases (e.g. name-only vs name-only with no identifiers) but nothing an agent needs to call it correctly 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%, so the baseline would be 3, but the description adds real meaning the schema lacks: it explains how 'a' and 'b' are actually compared (identifier equality first, normalised name similarity second) and which optional fields drive which signal. It does not address the asymmetry of name normalisation or case/format expectations for supplied identifiers.

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+resource ('Compare two company references') and the exact matching basis (company-number/LEI equality, normalised name similarity). It implicitly separates itself from resolution-style siblings like cross_registry_resolve by describing the comparison mechanism, but never names an alternative explicitly.

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?

Usage is only implied: the description sketches the 'one side UK company number, other side name only' scenario and the optional Companies House corroboration, which hints at when the tool is useful. There is no explicit when-to-use vs kyb_verdict/cross_registry_resolve guidance, and no stated exclusions or prerequisites.

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