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

Annotations already declare readOnly/openWorld/idempotent, so the description does not need to restate safety. It adds real behavioral value by disclosing the downstream id usage and the gotcha that location ids surface in `key` rather than `id`.

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?

Densely packed but front-loaded and every clause carries information (kind map, category_class values, catalogue exclusions, id/key caveat). The parenthetical arrows and pipe lists are terse rather than wasteful, though parsing takes effort.

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 an output schema present the description need not explain returns, yet it still flags the id/key distinction that would otherwise trip an agent, and it covers the parameter semantics, upstream/downstream coupling, and the edge cases for a 4-parameter search tool.

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 coverage is 0%, so the description carries the full burden and mostly delivers: it defines the accepted kind values as labeled enums and enumerates the valid category_class strings with examples, plus the empty-query listing behavior. Only `limit` is left entirely undocumented.

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?

States a specific verb and resource ('Searches Meta detailed-targeting entities by name') plus the return shape ('returns id + estimated audience size'). It enumerates the kind families, so an agent can distinguish it from sibling targeting tools like linkedin_targeting_search or tiktok_targeting_search.

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 says when each kind applies, that adTargetingCategory requires category_class, and that query may be left empty to list an entire class. It names the downstream consumers (create_meta_adset / update_meta_adset) and the alternative path for relationship status and education level, which are outside this catalogue.

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