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

Beyond the annotations (readOnlyHint, destructiveHint), the description explicitly lists what the tool does NOT do: fetch sources, access workspaces, store input, spend money, draft outreach, or send anything. It also declares deterministic scoring and review-only outputs, giving the agent a clear side-effect profile. This is excellent transparency.

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?

Two crisp sentences: the first states the purpose and outputs, the second lists explicit exclusions. Every sentence earns its place, and the key verb ('score') is front-loaded. No filler or redundancy.

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 tool with nested objects, 5 parameters, and an output schema, the description is shorter than ideal. It covers purpose, return type, and side-effect exclusions, but it does not provide usage context, prerequisites, or relationship to the sibling. The output schema exists so return values are covered, but an agent would still benefit from more guidance on how to structure inputs or when to invoke this tool versus prepare_why_now_review.

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 only 20%, so the description must compensate by adding parameter meaning. It does not: it only generically says 'caller-supplied business-account fit and buying-signal evidence' without explaining formats, defaults, constraints (e.g., maxItems, observedAt staleness, confidence semantics), or how parameters interact. The schema's property descriptions are doing the heavy lifting, but the description adds no value 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 opens with the specific verb 'score' and names the resource ('caller-supplied business-account fit and buying-signal evidence'), clearly distinguishing it from the sibling prepare_why_now_review. It also states the outputs (scorecard, evidence gaps, unsupported-claim flags), making the tool's role unambiguous.

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 implies usage by saying it scores caller-supplied evidence, and the negative list ('does not fetch sources...') tells the agent what this tool won't do — a weak form of when-not guidance. However, it never explicitly names the alternative (prepare_why_now_review) or states when to choose this over it, leaving the differentiation to inference.

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