List the exact pages assistants cite

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

Annotations only declare read-only and open-world, so the description carries the interpretive load and does: it explains the aggregation method ('adding up the period'), that `limit` is a top-N cutoff rather than a pagination cursor, and how `share` is computed. It also warns that citation is not visibility, a genuine behavioral caveat the agent could not infer from structure.

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 paragraphs, front-loaded with the defining distinction, then usage, then semantics. Dense but nearly every sentence carries non-redundant information; the citation-vs-visibility aside is valuable but slightly discursive.

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 return values need not be documented, yet the description still explains `share` and the ranking basis, closing the only interpretive gap. For a 4-param read tool with full schema coverage, nothing an agent needs is missing.

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 100%, so baseline is 3; the description exceeds it by clarifying that `limit` returns the most cited pages rather than a walkable list, and that `model` narrows to a single assistant. Date parameters are left to the schema, which is acceptable given full 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 resource (individual cited pages) and immediately fixes the granularity: 'each row is one URL, not a domain,' which distinguishes it from its nearest sibling list_sources. An agent can tell exactly what this returns versus the domain-level ranking.

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 an explicit trigger ('Call this when the domain ranking does not say enough') plus concrete motivating questions, and routes the agent to companions ('Read this beside list_prompts and list_competitors, not instead of them'). When-to-use and when-not-to-replace are both covered.

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