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

Annotations already declare this as read-only, idempotent, and non-destructive. The description adds value by specifying the ordering (live first, archived later), clarifying that the data is customer-declared (not verified), and explaining the conceptual split versus Surfaces. It does not contradict annotations and provides context beyond the structured hints, though it could mention pagination or error conditions.

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?

The description is verbose and includes tangential domain explanations about the Surfaces registry, control split, and logbook behavior. The core purpose is in the first sentence, but subsequent sentences add conceptual background that could be moved elsewhere or trimmed. It is not front-loaded and contains several non-essential details for an agent to call the tool correctly.

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?

Given a simple read-only list with one parameter and no output schema, the description adequately explains what is returned (fields), the ordering, and how it differs from candidates. It lacks explicit mention of response format (e.g., JSON array) but that is often implied. Overall, an agent can decide and invoke correctly without missing critical context.

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?

The schema covers the only parameter (project_id) with a clear description and pointer to list_projects. The tool description does not add any further meaning about the parameter beyond what the schema already provides, so the baseline of 3 is appropriate.

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 clearly states it lists the corroborations recorded for a project, specifying exactly what each entry includes (address, source domain, publication date, notes). It explicitly differentiates itself from sibling list_corroboration_candidates by noting that candidates are proposed pages the engines already showed, while this returns the customer-declared registry.

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?

The description contrasts corroborations with the twin registry of Surfaces, explaining the split is about control, not authorship or payment. It also mentions list_corroboration_candidates as the alternative for proposed pages, giving clear context on when to use this tool vs. that one. However, it does not explicitly state 'use this when you need the confirmed list' or list exclusion criteria beyond the contrast.

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