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

Annotations already declare the tool read-only and non-destructive, so the safety profile is covered. The description adds useful behavioral context: it returns only converting terms at or near target ACoS, covers SP + SB while excluding SD because no report exists, and notes the program label on rows. This goes beyond the annotations without contradicting them.

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?

Three short sentences front-load the core purpose, then specify the output criterion and program scope. Every sentence carries distinct information: what the tool finds, what filters the results, and what data it covers or excludes. 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?

With 14 optional parameters and no output schema, the description gives the core retrieval intent and partial return semantics but does not describe the output fields, default time ranges, or how the scoping parameters interact. It is enough for a basic call but leaves an agent without a clear picture of the returned rows or edge cases like empty results or date defaults.

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 71%, so the schema already documents most parameters. The description reinforces target_acos by mentioning 'at or near target ACoS' but does not add per-parameter semantics for the less-documented fields like limit, offset, or period_days. It adds general context rather than compensating for the remaining undocumented parameters.

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 specific verb and resource: 'Find converting search terms eligible for promotion to manual campaigns.' This clearly distinguishes it from generic search-term or optimization tools such as ppc_search_terms and ppc_negation_candidates by focusing on harvest candidates. It is not a tautology of the tool name and adds concrete output criteria.

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 context for use is clear: call this when the agent needs search terms that are converting and eligible to promote to manual campaigns, with ACoS near target. It does not explicitly list alternative tools or state when not to use them, but the purpose statement and coverage caveat ('SD has no search-term report') provide enough directional guidance.

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