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

The description adds meaningful behavioral details beyond the annotations: the operation is one-way, ciphertext remains afterward, the landlord cannot perform it on the citizen's behalf, and occupancy is unchanged. These side-effect and permission constraints are not captured by the annotations and help an agent predict what invoking this tool does.

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 four short, front-loaded sentences, each providing a distinct fact: endpoint/action/auth, one-way behavior, ciphertext persistence, delegation restriction, and occupancy side effect. There is no filler, repetition of schema content, or unnecessary exposition.

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 rich per-parameter schema descriptions and the presence of an output schema, the description covers the essentials: what the tool does, how to authenticate, and what side effects to expect. It does not spell out the controller-signature parameter combination or auth alternatives, but the schema already carries most of that burden, so the description is close to complete.

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?

The input schema already documents nonce, leave_token, controller_signature, and controller_public_key, covering 80% of parameters. The description supplements the undocumented `bag` by identifying it as the leftover plaintext to be sealed, and it provides the request payload shape `{action:"seal", bag}` plus the Bearer Authorization mechanism, which adds meaning beyond the schema.

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 verb and resource: POST /api/locker with action "seal" on a bag, and describes it as a one-way sealing of plaintext into ciphertext. It distinguishes itself from occupancy-moving or landlord-performed actions, though it does not explicitly name sibling tools like locker_write or locker_purge.

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?

The description gives useful contextual signals: it is for leftover plaintext, requires the citizen's own key, cannot be done by the landlord, and does not move occupancy. However, it never explicitly says when to prefer this over locker_write/locker_purge or what conditions trigger its use, so the guidance remains mostly implied.

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