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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's added value is the default ranking ('most reviewed first') and the pagination mechanism ('Page with next_cursor'). That is genuinely useful behavioral context beyond the structured fields, though it omits rate limits or result-shape caveats.

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?

One dense, front-loaded sentence: purpose first, then parameter semantics, then pagination. Nothing is wasted, though the colon-chained clauses make it slightly harder to scan than a bulleted form would be.

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 an output schema present, return values need no explanation, and the description covers ranking, filtering, and pagination for a 5-parameter optional-input tool. The only gap is the absence of any note on when to prefer this over single-subject read 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 80%, so the baseline is 3; the description goes further by giving concrete examples of what 'query' matches (a host, a path, a package) and spelling out the full enum-like set for 'type' and the semantics of sort=recent. This adds real interpretation value over the terse schema descriptions.

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 ('List reviewed subjects') plus the default ordering, which clearly identifies it as a discovery/search tool. It does not explicitly differentiate itself from siblings like read_subject or resolve_subject, but the 'search/list reviewed' framing separates it from single-subject reads.

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 explains how each parameter influences results (query matches key text, type narrows, sort=recent reorders), which implies when to use it, but it never states when this tool is preferable to read_subject, resolve_subject, or other discovery tools. Usage context is implied rather than declared.

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