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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description adds real behavioral context: fixed 20-per-page pagination, ordering by reference count, the absence of a limit argument, and that stored evidence is read without fetching URLs or launching a Scan. It stops short of stating rate limits or cursor expiry, hence 4 rather than 5.

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?

Dense but front-loaded: the scope, page size, and return shape come before pagination and routing advice. Every sentence carries information, though the cursor/nextCursor and 'same filters' phrasing is slightly repetitive and could be tightened.

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-value explanation is a bonus rather than a requirement, and the description nonetheless states what is returned and what is not. However, for a 12-parameter tool with 17% schema coverage, the filter semantics that drive this reference query are largely unexplained, leaving a meaningful completeness gap.

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 only 17% across 12 parameters, so the description carries the burden of explaining filters. It clarifies cursor handling ('Follow nextCursor with unchanged filters') and scanId selection via list_scans, but gives nothing for tag, stage, region, persona, product, category, platform, promptId, or brandMention, leaving most filtering semantics opaque.

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 uses a specific verb and resource ('Read cited source domains across eligible Scans') and immediately states the pagination unit and ordering ('fixed 20 per page ordered by reference count'). It explicitly separates itself from the sibling get_reference_domain, so an agent can route between them without opening either 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?

Explicit alternative routing: 'Use get_reference_domain for exact stored pages and date/Scan history, passing this scopeToken and the same filters,' plus the dependency 'For a date period select Scan IDs using list_scans.' It also states the negative ('Reading stored evidence never fetches URLs or launches a Scan'), giving clear when-not guidance.

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