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

Beyond the readOnly/openWorld/destructive annotations, the description adds substantive behavioral disclosure: every fact remains labeled caller-supplied and unverified, and the tool does not research, infer budget or buyer intent as fact, draft outreach, access private data, persist input, or take action. This is rich, specific context that helps set correct expectations. No annotation contradiction.

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 is three sentences with the core purpose front-loaded, followed by the provenance guarantee and a tight list of exclusions. Every sentence carries meaningful information and there is no filler.

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 the tool's nested 5-parameter schema and existing output schema, the description covers the crucial non-goals and provenance well. It does not explain account/vendor or date semantics, but the schema and output schema carry those details, so the description is largely complete for safe 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 schema description coverage at only 20% for top-level parameters, the description was expected to compensate, but it only names two input categories ('fit criteria' and 'business signals') and adds a global provenance invariant. It does not clarify the roles of account, vendor, or asOfDate, nor the shape of the inputs, leaving a notable semantics gap beyond what the sparse top-level schema provides.

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 transformation ('Turn caller-supplied fit criteria and business signals into reviewable why-now and fit guidance') and clearly scopes the tool to review preparation rather than research or outreach. It differentiates by listing non-goals (does not research, infer, draft, access private data), although it does not name the sibling tool 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?

The description implies when to use the tool—when caller-supplied fit criteria and signals exist and reviewable guidance is needed—and clearly lists what the tool will not do. However, it provides no explicit when-not-to-use guidance or routing to the sibling tool 'score_buying_signal_evidence', leaving some selection burden on the agent.

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