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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety and external-network reach are covered. The description adds one genuinely useful behavioral fact beyond that: results may include audience size 'where available', which signals inconsistent return fields. It doesn't say how many results come back, whether matching is prefix or fuzzy, or whether audience-size lookups are slower or rate-limited.

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?

A single sentence that front-loads the action ('Find targeting IDs') and then qualifies the entity types and the returned audience size. No filler, no restatement of the tool name, nothing an agent must skip past to reach the operative information.

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 six parameters, no output schema, and an open-world search backend, the description should say more about what comes back (ID plus name pairs? a ranked list?) and any result limits. It covers entity types and the audience-size caveat but not the return shape, the meaning of the optional scoping parameters, or the relationship between location results and the `country` filter. Workable, not complete.

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?

The description expands the `location` option into 'countries, regions, cities', which adds real meaning beyond the bare enum value. However, with only 67% schema coverage, three parameters (folder, account, language) carry no explanation in the description, and it doesn't clarify how the `country` parameter interacts with `type=location`. Added value is real but partial.

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?

Specific verb-plus-resource: 'Find targeting IDs' for interests, behaviours, or locations, with the search mechanism (keyword) and the value-add (audience size). It clearly separates the three searchable entity types covered by the `type` enum. It doesn't distinguish itself from sibling lookup tools like meta_audiences or linkedin_targeting_search, but the platform prefix in the name plus the explicit entity list makes the purpose 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?

Usage is only implied: an agent can infer this is the lookup step before applying targeting via meta_update_targeting or meta_create_adset, but the description never says so. There is no guidance on when to prefer this over meta_audiences/meta_saved_audiences (existing vs. new targeting), nor any note that results are IDs meant to be passed downstream. Adequate but leaves the routing decision to inference.

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