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

With no annotations provided, the description carries the full burden. It discloses that it does not mutate TikTok and that the returned approval_ref is single-use, which are key behavioral traits. It does not mention authentication, rate limits, or failure behavior (e.g., what happens on validation failure). For a validation tool, the disclosed traits are helpful but not exhaustive.

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 with zero redundancy. The main purpose is front-loaded, and the second sentence adds two crucial clarifications (non-mutation and alias) without wasted words. It is concise and well-structured.

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 7-parameter tool with no output schema and no annotations, the description is incomplete. It covers the core action and the alias, but does not explain the roles of the various ID/version parameters, the idempotency mechanism, or the expected output format beyond 'approval_ref.' An agent might correctly invoke it but lacks understanding of prerequisites or postconditions. The description is adequate but not complete for a complex 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?

Schema description coverage is only 14% (only target_value has a description). The description adds the critical clarification that adset is an alias for ad_group, which is essential for interpreting entity_type. However, it does not explain run_id, rule_id_and_version, idempotency_key, or the meaning of 'bounded' and 'tenant-owned' in relation to parameters. The low coverage means the description should compensate more than it does.

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 action: validate a bounded budget change and return a single-use approval_ref. It names the resource types (campaign, ad_group) and explicitly clarifies that adset is an alias, which distinguishes it from similar tools like budget_confirm. This is a clear, non-tautological 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?

It explicitly states 'does not mutate TikTok,' which implies this is a preparation step, not the final commit. However, it does not name sibling tools like budget_confirm or bid_prepare as alternatives or provide explicit when-to-use guidance. The context of the sibling list (prepare/confirm pairs) makes usage inferable but not explicit.

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