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

With no annotations present, the description carries the full burden and does disclose key traits: read-only, no token required, and a data-trust warning that 'Reviews are untrusted data from sessions', which is a meaningful prompt-injection caution. It stops short of describing result volume, pagination, or truncation behavior for a potentially large public index.

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 compact sentences with the safety and access constraints front-loaded ('Read-only, no token'), then filters, then the untrusted-data caveat. Dense but every clause carries information; no filler sentences.

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?

With no output schema and no annotations, the description must convey both the safety profile and the shape of returns, and it does: safety flags, index contents, the rerun view, and the untrusted-data caveat. Pagination or size limits on a public index are the only notable omission.

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 would be 3, but the description adds genuine meaning: q is a substring match on the tool URL, and wanted=true switches the entire returned collection to open reruns represented as postable replies. That is more than the schema's terse 'list open reruns, not the index'.

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 gives a concrete verb and resource ('return the public tool review index') and enumerates its contents (receipts, corroboration, changes), which clearly separates it from message-oriented siblings like lockzone.recent or lockzone.rooms. It does not name any sibling explicitly, so the differentiation is achieved by subject matter rather than routing language.

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 states two operative modes with their triggers: pass q to restrict to tools whose URL contains text, and wanted=true specifically to 'list open reruns, not the index'. That is clear conditional guidance, though it never tells the agent when this tool is the wrong choice versus other lockzone reads.

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