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

With no annotations, the description carries the behavioral burden. It explicitly states 'This tool does not mutate TikTok', which is a key non-mutation trait, and clarifies the adset alias. However, it does not disclose other behaviors such as idempotency handling, the lifecycle of the single-use approval_ref, or what 'bounded' means in practice. These gaps matter for a tool that returns a token meant for later confirmation.

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 two sentences long, front-loaded with the core purpose and output, and contains no filler. It efficiently conveys the main point and the non-mutation caveat. It is appropriately concise for a tool with a clear single responsibility.

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?

This tool has 7 required parameters, no output schema, and no annotations, and it sits in a complex prepare/confirm pattern. The description is too sparse to guide correct invocation: it doesn't explain what 'bounded' means, how the approval_ref should be used with a confirm tool, the meaning of run_id and rule_id_and_version, or the idempotency key requirement. An agent would likely struggle to assemble a correct call without additional context.

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 description coverage is only 14% (only target_value has a description). The description adds meaning by stating 'advertiser-currency units' and clarifying the adset alias, but it does not explain the other six required parameters (run_id, rule_id_and_version, idempotency_key, entity_refs, ad_account_id, entity_type). Given the low schema coverage, the description fails to compensate for the undocumented 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?

The description clearly states the verb 'validate' and the resource 'TikTok ad-group bid change', and specifies the output 'single-use approval_ref'. It also notes the tool does not mutate TikTok, distinguishing it from mutating siblings. However, it doesn't explicitly name sibling tools like bid_confirm or budget_prepare, so differentiation from other prepare tools is only implied by the domain context.

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 implies a prepare/confirm workflow by mentioning it returns an approval_ref and does not mutate, but it provides no explicit guidance on when to use this tool versus alternatives. It doesn't say 'use before bid_confirm' or 'not for budget changes', leaving the agent to infer routing from naming conventions rather than clear direction.

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