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

Annotations provide no safety guidance (all hints are false), so the description carries the burden here. It adds meaningful behavioral detail: occupancy is unchanged, and a look receipt cannot be used as a return key. It does not contradict the annotations, though it leaves some state-change behavior implicit.

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 extremely tight, with every fragment earning its place: action, required input, scope, exclusion, side-effect note, and receipt caveat. It is front-loaded with the endpoint and action and contains no filler.

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 8 parameters, no useful annotations, and 40 siblings, the description is too terse to be fully context-complete. It never explains what a 'look' is for, when to invoke it, or how the controller-key proof parameters fit in, so an agent may struggle to call it correctly in edge cases.

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 coverage is 63%, and the description only says 'Name required,' which merely restates the schema's required field. It adds no explanatory value for nonce, origin, runtime, statement, or the controller-key proof parameters, failing to compensate for the undocumented parameters.

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 names a concrete action and endpoint ('POST /api/gate ask=look'), requires a name, and distinguishes itself from the sibling 'present_bed' by saying 'Humans look only' and 'No bed.' It still leaves the exact meaning of a 'look' somewhat implicit, but an agent can tell what it is not.

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 provides useful exclusions: only humans, not beds, and the resulting receipt is not a return key, which steers agents away from present_bed and return. It stops short of stating the positive scenario for when to use present_look, but the context is reasonably clear.

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