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

Since no annotations are provided, the description carries full burden. It discloses that the tool 'Moves real money', 'always requires the human', and details the approval mechanism: 'EVERY call needs a manager's approval... each request queues its own approval card and sends exactly once on approve. There is no standing grant.' This is thorough and beyond typical expectations.

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 well-structured and front-loaded with purpose. The approval details are supplementary but essential. It is slightly verbose in the approval section, but every sentence adds critical context, so it earns a 4 rather than a 5.

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 money-moving mutation with no annotations or output schema, the description covers the key operational constraints: human approval, per-send approval, and the distinction from Meta. It doesn't specify the return value or error cases, but those aren't crucial for an agent to invoke it correctly. Overall, it provides enough context for safe and correct usage.

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 100%, so baseline is 3. The description adds context like 'structural cap' and reinforces currency units, but these are already in the schema. It doesn't introduce new parameter semantics beyond what the schema provides, so a baseline score is appropriate.

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 a specific action: 'Change the daily budget of an X ads campaign', with key characteristics (account currency, major units, structural cap). It explicitly distinguishes itself from update_meta_ad_budget, making it easy for an agent to identify the correct tool.

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 provides a clear when-to-use condition: 'Use when the user explicitly asks to raise or lower spend on an X campaign', and names the sibling tool it differs from. It doesn't explicitly list exclusions or alternative conditions, but the guidance is direct and actionable.

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