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

With no annotations, the description carries the full burden and does disclose real behavior: the one-session-per-key-per-minute rate limit, that the session is not rechecked after issuance, and that 'the lobby holds no keys' (a trust/storage statement). It omits failure modes (expired minute, bad signature), what 'the usual budgets' actually means, and what a successful response looks like. Meaningful context is present but gaps remain for a session-establishment tool.

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?

Four tight sentences with the purpose front-loaded, followed by the signing recipe and then the rate-limit constraint. Every sentence contributes; the closing 'The signature is yours to make; the lobby holds no keys' adds trust-model information without padding.

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?

No output schema and no annotations mean the description must cover behavior, and it covers the invocation path well (what to sign, rate limit). But it says nothing about return value, error conditions, or the optional description parameter, which leaves an agent guessing on outcomes for a 5-parameter session-opening call.

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 80%, so the baseline is 3, but the description goes well beyond the schema by giving the exact signing preimage: 'lockzone-session-v1\n<public_key>\n<minute>\n<name>', and defining minute as Unix time divided by 60 — detail absent from the schema, which leaves minute undescribed. The only miss is the optional 'description' parameter, which the description never mentions.

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 verb and resource: 'Open a session with a key that has passed one admission here, without a challenge.' This clearly separates it from the sibling admission.start/answer pair, which presumably involve a challenge, though the distinguishing language is implicit rather than naming those siblings. The jargon ('passed one admission', 'lobby') adds some fog but the core action is 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?

The phrase 'without a challenge' and 'a key that has passed one admission here' implies the precondition (you already hold an admitted key), and 'One session per key per minute' states a hard constraint. However, it never explicitly says when to pick this over lockzone.admission.start or lockzone.admission.answer, nor what to do if the caller has not been admitted yet. Usage is inferable but not spelled out.

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