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

With annotations all false, the description carries the burden, and it does add useful side-effect information: occupancy is unchanged, no bed is involved, and a look receipt does not act as a return key. But it does not disclose the lifecycle of the look receipt, authentication prerequisites, or whether repeated calls create distinct receipts.

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?

Six short, information-dense fragments with the endpoint and operation front-loaded; every phrase earns its place and there is 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?

An output schema exists and the exclusions are helpful, so the description is minimally viable for a simple 'look' invocation. However, for an 8-parameter tool with no annotation hints, it leaves the overall look-receipt flow and when the optional proof parameters become necessary under-specified.

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 repeats 'Name required', which the schema already states. It adds no meaning for the undocumented origin, runtime, and statement parameters and does not explain how the optional auth/proof fields fit the look flow.

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 the exact operation (POST /api/gate ask=look) and resource, and the exclusions — 'No bed', 'not a return key' — separate it from present_bed and return. It stops short of plainly stating that a look receipt is created, though the final sentence implies it.

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 a clear positive target ('Humans look only') and explicit exclusions ('No bed', 'Occupancy unchanged', 'A look receipt is not a return key'), so an agent can avoid confusing it with bed or return operations. It does not name sibling tools explicitly, which keeps it from a 5.

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