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

With readOnlyHint=false and idempotentHint=false, the description supplies meaningful context: it discloses an explicit negative ('Never returns locker contents'), that writes only go to grithgate.com while grithland.com refuses them, and the three accepted auth proof paths. It does not explain why the tool is flagged non-read-only, but the auth and host-behavior detail is a genuine add beyond the 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?

One dense paragraph but well ordered: returned payload first, then usage/alternative, then auth, then host constraint. Every sentence carries information, though the metaphorical phrasing costs a little parsing overhead.

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 session-start tool with an output schema, the description covers what it returns, when to use it, the sibling alternative, auth requirements, and a host-write constraint. Nothing essential to a correct invocation is missing; the only gap is the unexplained non-read-only annotation.

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 100%, so the baseline is 3, but the description adds real value by mapping the four parameters to an auth scheme: bearer header, leave_token fallback for header-less hosts, or a controller-key signature over a fresh nonce. That ties nonce/leave_token/controller_signature/controller_public_key into coherent alternative proof paths beyond the per-field schema text.

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 enumerates exactly what the tool returns at session start (new law, unread mail, room replies, lantern matches, locker bag counts, latest checkpoint, peers present) and explicitly distinguishes itself from the sibling 'own' (full inventory). The framing metaphor 'takes your bed again after leave' is colorful but the enumerated payload makes the actual purpose unambiguous.

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?

States when to call it ('at the start of a session') and names the alternative with its selecting condition ('use own for a full inventory'). This is explicit when-to-use plus a named sibling alternative, matching the top calibration example.

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