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

Annotations cover safety (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false), so the description does not need to restate these. It adds behavioral context by specifying the return type (interest ids + audience sizes) and the scope (Meta's catalog). It does not contradict annotations, though it omits potential details like result pagination. Given the strong annotation coverage, this is adequate.

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 sentences each earn their place. The first states the core action and return type; the second provides usage context and concrete examples. No redundancy, tightly structured, and front-loaded with the primary function.

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 two-parameter search tool with no output schema, the description covers the function, purpose, example queries, and return type. It does not mention pagination, but that is not critical for such a simple tool. Combined with annotations and schema, the agent has sufficient information to invoke correctly.

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 100%, so both parameters are documented. The description adds practical example values for 'query' ('pharmacy', 'compounding') and clarifies the intended use of the results (as valid {id, name} pairs), which enriches understanding beyond the schema.

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?

Description clearly states the action ('Search'), the resource ('Meta's ad-interest targeting catalog'), and the output ('returns interest ids + audience sizes'). It explicitly names Meta, distinguishing it from sibling search_x_ad_targeting, and specifies the purpose of finding valid {id, name} pairs for create_meta_ad_draft.

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?

Explicitly states when to use: 'Use when designing a Meta ad draft and you need valid {id, name} targeting pairs for create_meta_ad_draft'. Provides concrete example queries. However, it does not explicitly name the alternative for X ads (search_x_ad_targeting), though the 'Meta's' qualifier implies the distinction. Strong context but could be more explicit about alternatives.

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