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

The description adds substantial behavioral detail beyond the annotations: status changes on widening vs narrowing, the rolling 30-day meaning of monthly_cap, replacement semantics for identical category sets, and the handoff-not-error behavior for missing coverage. These are exactly the non-obvious behaviors an agent needs to predict consequences correctly.

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 dense but well-organized: action menu first, then critical behavioral caveats, then the rolling-window definition, then replacement semantics, then the handoff clarification. Every sentence earns its place and the material is front-loaded for quick action selection.

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?

Given the tool's complexity (6 parameters, nested scope object, enum actions, output schema present), the description covers the essential semantics: action requirements, approval behavior, window semantics, and edge-case handling. The output schema handles return values, so nothing necessary for correct invocation is missing.

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?

Although the schema already documents all parameters (100% coverage), the description enriches their meaning: monthly_cap is tied to a rolling 30-day window from creation, scope carries status-transition implications, and update's effect on approval state is explicitly called out. This goes well beyond the baseline expected for fully documented schemas.

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 'AP2 spend mandates' and immediately enumerates four specific actions (request, list, update, revoke), each with its required inputs and expected result. This clearly identifies the resource and the operations, and the action-specific details prevent confusion with other payment-related tools.

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 action routing: request needs scope, update needs mandate_id+scope, revoke needs mandate_id. It also warns that update NEVER approves, giving clear selection guidance within the tool. It does not explicitly contrast with alternative sibling tools, but no sibling appears to overlap with spend mandates.

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