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

Annotations declare destructiveHint=true and idempotentHint=false, and the description adds crucial context beyond them: changes are staged and require human approval before execute_approved_action, with administrator-configurable requirements. This meaningfully clarifies the real-world effect of a destructive mutation.

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?

Front-loaded with the use-case clause and four concise sentences with no obvious redundancy. The approval boilerplate is somewhat generic but earns its place as behavioral context.

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 destructive mutation with a rich nested schema and an output schema, the approval-workflow disclosure is complete for the safety story. But with 0% parameter coverage and the nested update payload unexplained, an agent still lacks what it needs to call it 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?

Schema description coverage is 0%, and the nested 'data' object has many undocumented fields. The description only says 'allowed fields' without indicating which fields (name, status, dates, etc.) are updatable or their constraints, so it fails to compensate for the coverage gap.

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?

States a clear verb+resource: 'Update allowed fields of permit' within RetailHardHat permits records. An agent can distinguish it from create_permit/delete_permit/get_permit. However, it never clarifies which fields are 'allowed', leaving scope somewhat opaque.

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 provides meaningful context about the approval workflow (no change until human approval and execute_approved_action). But 'Use this when working with permits records' is generic and doesn't explicitly differentiate from siblings like update_permit_document or the approval-request tools.

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