approve

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

With no annotations, the description carries the full behavioral burden. It usefully discloses 'Fails closed' and the purpose of surfacing the gate in chat, but says nothing about what happens on approval vs denial, timing, or what the caller receives. Partial disclosure for a safety-relevant tool.

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?

Purpose is front-loaded in the first sentence, with the wiring detail and fail-closed behavior after. Three tight blocks with no filler, though the code-span wiring string is somewhat niche.

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 bridge tool with no annotations, no output schema, and 0% param coverage, the description covers purpose and the fail-closed guarantee but omits parameter meaning and return/approval semantics. Adequate to understand the concept, not quite enough to invoke confidently.

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% across three parameters (tool_name, input, room_id), so the description must compensate. It implies a tool call is being approved but never names or explains any parameter, leaving room_id and input entirely undocumented in both places.

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 states a specific and unusual function: a permission-prompt bridge that asks a human in the room to allow a tool call. That verb+resource framing clearly separates it from every sibling (none of which gate permissions). The generic name 'approve' is rescued by the description.

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 gives concrete when-to-use context: wire it as Claude Code's permission-prompt-tool so a headless wake hitting a permission gate surfaces in chat instead of stalling. It stops short of naming explicit alternatives or when-not-to-use, but no sibling competes for this role, so the guidance is effectively clear.

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