mutate

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

Beyond annotations (write-only, open-world, non-destructive), the description reveals critical behaviors: the dry-run diff with token confirmation, capability-table governance, refusal of unruled/forbidden operations, and that 'every update reads the current values first, so the journal can undo it.' This substantially exceeds what annotations alone communicate and does not contradict them.

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 compact and well-organized: purpose first, then workflow/behavior, then a clear routing preference. Every sentence contributes – there is no filler, and the most decision-relevant information is front-loaded.

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 general write path with 7 parameters, an output schema, and annotations, the description covers the essential operational context: capability-table governance, two-step confirmation, safety via undo journal, and the existence of more specific siblings. It provides enough for an agent to invoke correctly, and where specifics are lacking, it points to the governing mechanism (capability table).

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. It effectively explains confirm_token ('Call it once with no confirm_token to see the exact diff... and a token') and dry_run implicitly through the two-step flow. It also gives meaning to resource and operation through the 'change any mutable resource' framing. However, fields_json and resource_name are not semantically described, leaving some parameters unexplained.

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 'Change any mutable Google Ads resource' – a specific verb and resource scope – and immediately positions it as 'the general write path' that 'reaches every resource the API exposes.' It explicitly contrasts itself with specific sibling tools like pause_keywords, making its role unmistakable. This is a clear, differentiated statement of purpose.

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 explicit guidance: 'Prefer the specific tools where they exist – pause_keywords and the rest measure evidence this path cannot.' It also explains the exact two-step invocation pattern ('Call it once with no confirm_token... Call it again with that token'). This tells an agent both when to use this tool and when to choose an alternative, with no inference required.

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