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

The description adds valuable behavioral context beyond the annotations: it notes the tool 'Returns a draft for human review', mentions 'Price: 0.25 USD', and 'Payment requires explicit wallet authorization'. It also discloses the constraint of no outbound actions. These are not covered by the annotations (readOnlyHint=false, destructiveHint=true), so the description fills gaps without contradicting the schema. The destructiveHint is not explained, but the description implies a non-destructive analysis output, so no 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, front-loading the core purpose in the first sentence. It includes essential cost and authorization details without redundancy. Every sentence adds value—purpose, scope, and payment—so it is appropriately concise and well-structured.

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?

The tool has 5 parameters, a nested object, and no output schema. The description is too brief to cover the complexity. It does not explain the input structure (e.g., what goes in 'brief' vs 'source_text') or the meaning of optional fields like idempotency_key or result_signature. While the schema defines the structure, the description should provide semantic context for how to populate these fields to achieve the mapping goal. The mention of 'draft for human review' hints at the output but does not describe the result format. This is insufficient for a tool with such an elaborate schema.

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 0%, so the description must compensate for parameter meaning. However, the description does not map its actions to the actual schema fields. It mentions 'supplied keywords' and 'pages' but the schema has 'brief', 'audience', and 'source_text' within the 'input' object, plus several optional parameters like result_expires and payment_signature. The description does not clarify what these fields represent or how they relate to the mapping task. The agent would have to infer the mapping from names alone, which is insufficient.

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 action: 'Map supplied keywords to supplied or proposed pages', and includes distinct behaviors like 'flag cannibalization' and 'separate existing from proposed URLs'. This clearly differentiates it from siblings like keyword_cluster (grouping) or internal_link_plan (link placement). The purpose is 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 provides clear context: 'Uses buyer-supplied information only; no external research or outbound actions.' This tells the agent when to use the tool (when working with buyer-provided data). However, it does not explicitly name alternatives or state when NOT to use it, so it lacks exclusions. This earns a 4 rather than 5.

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