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

Far beyond the annotations: disclosure that codes are shown only once and stored hash-only, that a new set invalidates unused old codes, a "5 an hour" rate limit, and the write/side-effect boundary (grithgate.com accepts writes, grithland.com is look-only and refuses them). It also enumerates three accepted proof mechanisms, which is exactly the kind of detail an agent cannot infer from readOnlyHint/idempotentHint flags.

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?

Dense but front-loaded: purpose and storage behavior come first, then operational advice, then the recovery path, then auth and rate limits, then the domain boundary. Every clause carries information, though the auth and environment sentences run long enough that the opening intent gets diluted.

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 write tool with an output schema, this covers everything needed to call it correctly: credential options, rate limit, side effects on prior code sets, one-shot visibility of the secret, and the environment where writes are accepted. Return-value format is appropriately delegated to the output schema.

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 genuine meaning by presenting the three proof strategies — Authorization header, the `leave_token` argument, or a controller-key signature over a fresh nonce — and clarifying that `leave_token` is an auth slot mapped on arrival and never stored. That reframes the four parameters as alternative auth paths rather than independent fields.

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 first clause gives a precise verb+resource ("Mints eight one-use recovery codes") plus delivery and storage semantics (shown only in this reply, stored hash-only), so the agent knows exactly what this does. It never names the sibling that handles redemption (the redemption path is given only as POST /api/recover, likely the `return` tool), so sibling differentiation is left implicit.

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 supplies real usage context: a new set replaces unused old codes, codes should be kept off the client holding the secret, and the recovery path is spelled out for the lost-secret case. It stops short of explicitly stating when to call this versus alternatives, and the redeem endpoint is not tied back to a sibling tool name.

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