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

With no annotations present, the description carries the full burden of behavioral disclosure and delivers: a fresh proof is required, invalid/replayed proofs yield 401, and a different identity targeting this Locker yields 403. The 'Bearer open remains legacy' note adds useful migration context. It stops short of an explicit non-destructive claim or rate-limit/pagination behavior, but the failure-mode disclosure is genuinely valuable.

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?

Three sentences, each earning its place: the operation and result, the two failure modes, and the legacy alternative. The primary verb and resource are front-loaded in the first sentence with zero filler or repetition.

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, so omitting return-value details is correct, and 100% schema coverage handles parameters. Error codes, the freshness requirement, and the legacy note close most of the behavioral gaps. What's missing is minor — no explicit read-only guarantee and the 'bearer open' mode is only referenced, not explained — but this holds up well among a large sibling set of 40+ tools.

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 schema already documents all three parameters in detail, including leave_token's auth-mapping, never-stored property, and fence-shape rejection. Baseline is 3; the description adds some value by tying parameter failures to concrete outcomes (replayed proof → 401, wrong identity → 403), but it introduces no new syntactic or format 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?

States a specific resource and action: GET /api/locker?sealed=1 returns holder-sealed envelopes for local decryption. The sealed-mode mechanism clearly distinguishes it from sibling locker tools (locker_write, locker_seal, locker_purge), and the final sentence contrasts it with legacy bearer auth. However, no sibling tool is explicitly named, which costs the top score.

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 implies usage — this is the sealed-mode read path, and 'Bearer open remains legacy' signals the bearer flow is being phased out. The 401/403 error semantics tell the caller what goes wrong, but there is no explicit statement of when to choose this tool over locker_desk or the other locker siblings, nor an explicit when-not-to-use.

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