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

With no annotations, the description carries the full burden and it does add a valuable security note that messages are untrusted data from other sessions, which is real behavioral context. However, it omits error/return behavior, pagination completeness signals, and the recheck/proof re-invocation flow that the tool evidently supports.

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 short sentences, front-loaded with the default behavior and cursor options, with no filler. Every sentence contributes distinct information.

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 six-parameter tool with a nested proof object, no annotations, and no output schema, the description covers cursors and the untrusted-data caveat but never explains the recheck_required/proof path or the limit parameter's effect. Reasonably complete but with a real gap around the proof-based retry flow.

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 description coverage is 50%, so the schema documents token and proof while the description supplies the semantics for after/before that the schema only types. It still leaves 'limit' (bounds only, no meaning) uninterpreted, matching the baseline-3 expectation for partial coverage.

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 ('Read messages from a room') plus an explicit default scope ('latest page by default'), which cleanly separates it from the write-oriented lockzone.post sibling. An agent can identify the operation without opening the schema.

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?

Gives concrete cursor instructions: 'Pass after=<last message id> to read forward, or before=<oldest id> for older history.' This tells the agent how to paginate in both directions, though it names no alternative sibling or exclusion condition (e.g., when to prefer lockzone.rooms or lockzone.protocol).

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