direct_set_autotargeting

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

With no annotations, the description takes on the full burden and does so well: it signals the mutation ('WRITE'), names the underlying API method, warns about the array gotcha ('Prefer plain array'), and explains that allow_write=true is required. It does not detail side effects like replacement of existing categories or auth requirements, but covers more than the minimum.

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?

The description is front-loaded with the WRITE marker and uses a compact, information-dense structure. Every sentence carries useful information: the API method, categories format and examples, the array gotcha, optional bid_rub, and the allow_write guard. No filler or redundancy.

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 mutation tool with no output schema and 6 parameters, the description covers the critical aspects: the target entity, the categories structure, the guard flag, and a known API pitfall. It falls short of a 5 by not noting what the return value looks like or whether settings are additive/replacement, but it is sufficiently complete for safe invocation.

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 only 33%, so the description must compensate. It adds meaning to 'categories' with valid examples (EXACT, ALTERNATIVE, etc.) and the YES/NO value format, clarifies bid_rub goes via keywordbids, and emphasizes allow_write=true. It does not explicitly cover keyword_ids, project, or dry_run, but those are largely self-explanatory from their schema definitions.

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 opens with 'WRITE: keywords.update AutotargetingCategories for AT rows,' which clearly identifies the verb (update), resource (AutotargetingCategories), and scope (AT rows). This distinguishes it from sibling tools like set_keyword_states or set_keyword_bids, and the examples of categories further clarify what is being modified.

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?

The description gives clear context: it is a write operation for autotargeting categories, with an example and the requirement of allow_write=true. However, it does not explicitly state when to prefer this tool over alternatives or any exclusions, so it falls short of a 5 but provides enough context for a 4.

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