Approve every ready application in a batch

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

Beyond annotations (readOnlyHint=false), the description explicitly states the action is 'Records a human approval', confirming a write operation. It also discloses the safety mechanism preventing silent over-approval, which is not captured in annotations.

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?

Two sentences with no filler. Each clause provides distinct information: what it does, and the key prerequisite/constraint.

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?

The description covers the core purpose and critical prerequisite, and the schema covers parameter constraints. It doesn't describe return values or error behavior, but with no output schema and a simple write operation, the provided context is sufficient for an agent to select and invoke correctly.

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?

The schema describes manifestHash and expectedCount, but the description adds why they matter: binding approval to the exact packet set and preventing coverage of more applications than reviewed. It doesn't add detail for batchId or note, but these are straightforward.

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 uses a specific verb ('Records') and clearly identifies the resource ('human approval for each ready application in the batch'). It differentiates from sibling tools like approve_application by emphasizing the batch scope and the safety constraint.

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 states prerequisites: 'Requires the current manifest hash and the exact count being approved', which guides when to use the tool. However, it doesn't explicitly name alternative tools or state when not to use it, only implies it for batch-level approvals.

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