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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that these are TikTok's own platform suggestions (analogous to Google Ads recommendations), which is useful framing, but says nothing about pagination, filtering defaults, or scope limits beyond the level enum.

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, front-loaded with the core purpose followed by the level scoping. The 'level: ... | ...' tail is compact and earns its place by documenting the undocumented parameter values.

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?

An output schema exists so return values needn't be described, and annotations cover safety. However, a 2-parameter tool with 0% schema coverage and no usage routing leaves advertiser_id undefined and the relationship to apply/dismiss/list_recommendations unstated, so it is only adequately 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?

Schema coverage is 0% but the description supplies the meaningful part: the four level values (ACCOUNT, CAMPAIGN, ADGROUP, AD). That compensates for the missing enum in the schema. advertiser_id remains unexplained in both the description and schema, so coverage is only 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?

The description states a specific resource ('TikTok's own automatic optimization suggestions for an ad account') and scopes it with the level values, so an agent knows this is a retrieval tool for TikTok recommendations. It doesn't explicitly name the sibling it differs from (list_recommendations, apply_recommendation, dismiss_recommendations), but the verb+resource is clear.

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?

No when-to-use guidance is given. With siblings like list_recommendations, apply_recommendation and dismiss_recommendations in the catalog, the description never says whether this fetches, applies, or dismisses, nor when to pick this over those. Usage is only implied by the resource noun.

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