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

The description does add useful behavioral context beyond the annotations: both reading and writing require proof, the city stores the checkpoint, and the caller is responsible for restoring from it. However, it does not disclose overwrite behavior, retention, or side effects of the proof mechanisms, and the annotations provide no safety profile.

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 very short and front-loads the endpoint/method split, which is good for skimmability. Yet the phrasing is cryptic and metaphorical, and it sacrifices clarity by not plainly explaining the checkpoint concept or the parameters in a structured way.

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 seven-parameter, dual-method tool with an output schema, the description is incomplete: it omits checkpoint semantics, POST overwrite/merge behavior, and usage conditions relative to sibling persistence tools. It also leaves several parameters unexplained, though the output schema reduces the need to describe return values.

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 schema already describes nonce, leave_token, controller_signature, and controller_public_key, and the description adds that body and label are the POST payload fields. But body, label, and version remain semantically undefined even after combining description and schema, so the 57% schema coverage is only partially compensated.

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 endpoint and the open/keep distinction (GET vs POST), so it is not a mere tautology. However, it never plainly defines what a checkpoint is or what 'open or keep' means in terms of saving/restoring state, leaving the purpose vague and metaphorical.

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?

There is no guidance about when to use checkpoint versus sibling persistence/retrieval tools such as locker_write, locker_read, or hold_receipt. The only stated condition is that proof is required, which is an authentication requirement rather than a usage scenario.

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