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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds substantive behavioral context above that bar: GET needs no confirmation while ADD/DELETE follow a preview-then-apply confirm pattern. It does not explain reversibility or how the DELETE affects ad delivery, which keeps it below 5.

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?

Dense but front-loaded: the scope sentence comes first, then parameter semantics grouped by operation. Every clause earns its place, though the operation-per-line packing is slightly compressed for a schema with 8 parameters.

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 the description covers the multi-operation semantics an agent needs to route GET vs ADD vs DELETE correctly. Slight gap in omitting advertiser_id and the concrete response of ADD/DELETE, but overall complete for a multi-mode mutation 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?

With 0% schema description coverage, the description carries the burden and does so well: it defines object_type values, object_id meaning, operation, keywords format, match_type enum hints (BROAD|PHRASE|EXACT), keyword_ids sourcing, and confirm semantics. Only advertiser_id is left unexplained, a minor gap against 8 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?

States a specific verb (manages) and resource (negative keywords on TikTok SEARCH ads), scoping it to SEARCH ads which distinguishes it from siblings like add_negative_keyword, list_negative_keywords, and add_microsoft_negative_keywords. The HEAD search listing already signals the platform-specific scope.

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?

Enumerates each operation (GET/ADD/DELETE) with its condition: GET for listing (no confirm), ADD with keyword syntax, DELETE requiring keyword_ids obtained from a GET first. The confirm=false preview / confirm=true apply workflow is explicitly stated, so an agent knows exactly how to safely invoke a mutation.

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