Request Permission Escalation

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

Discloses that approval requires a human action (opening UI and clicking Approve), which is critical behavioral context beyond annotations. It adds the URL and process, and notes the non-self-approvable nature. No contradiction with 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 containing all essential info: what it does, that agent cannot approve, where to approve, how to poll, and a note about downgrading. Every sentence earns its place; front-loaded with purpose.

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 complexity (requires human approval, polling for result), the description covers the full workflow: request, human approval step, polling. It also addresses downgrading. No output schema needed as the polling tool handles results.

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?

Adds meaningful advice beyond schema: 'Be specific' for reason, 'Omit to use the active account' for account_id, and 'Must be higher than current preset' for target_preset. Schema coverage is 100%, but description provides extra guidance.

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 the tool's purpose: requesting an increase in permission preset. It explicitly distinguishes from checking status (check_escalation_status) and notes that downgrading doesn't require this tool. The verb+resource is precise.

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?

Explicitly states when to use: to request higher permissions. It tells the agent it cannot approve and must poll via check_escalation_status. It also clarifies that downgrading never requires a challenge, implying not to use this for reduction.

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