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

The description enriches the annotations by clarifying the deterministic behavior ('same input always gives the same answer'), which aligns with and expands on the idempotentHint=true annotation. It also details the three possible return states ('matched', 'ambiguous', 'none') and explains the handling of misheard names and fuzzy company hints, all of which go well beyond the structured fields.

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 packs a lot of value into two sentences, with the core purpose front-loaded and usage guidance inserted as an aside. The dash-heavy relative clause ('— same input always gives the same answer—') is slightly redundant with 'deterministically' but reinforces the key point. It could be marginally tighter, but it remains efficient and well-ordered.

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 that an output schema exists (likely documenting the return format) and the annotations already establish the safety profile (readOnly, idempotent, non-destructive), the description fully covers the operational semantics. It tells the agent what the tool does, when to use it, how it behaves with ambiguous input, and what to expect in return, leaving no critical gap for a typical invocation.

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?

With 100% schema coverage, the base is 3, but the description adds value by explaining that 'name' may be misheard and 'company' serves as a disambiguation hint that 'sharply improves disambiguation.' This contextualizes the purpose of both parameters beyond the schema's mechanical descriptions, justifying a score above the 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 opens with a precise, verb-driven statement: 'Deterministically resolve a (possibly misheard) name — optionally with a company hint — to ONE person in the network.' This clearly defines the action, resource, and scope while setting it apart from siblings like search_people or get_person. The phrase 'PREFER THIS over hand-rolled search_people ladders' explicitly differentiates it from a key sibling, leaving no ambiguity about its purpose.

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 includes an explicit usage directive: 'PREFER THIS over hand-rolled search_people ladders whenever the task is "who is X?" from a voice note, capture, or mention.' This tells the agent exactly when to choose this tool and hints at the alternative (search_people). While it does not list exclusions, the 'whenever' clause is specific enough to guide correct selection.

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