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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavioral facts: newest-first ordering, a hard 50-per-page cap, and cursor-based continuation. It stops short of stating whether a total count or empty-page signal exists, so not a 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?

Three tight sentences with zero filler; the core purpose, ordering and pagination constraints come first, and the optional include behavior is deferred to the end where it belongs.

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, the description usefully covers the return payload (URL plus domain per citation) and pagination mechanics, which is the key missing structure. It omits any mention of the response_id filter, a slight gap for a four-parameter tool, but everything needed to call it correctly is present.

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 the schema already documents cursor, include, project_id and response_id, and the description largely echoes that (include loading parent chains, nextCursor as the continuation token). It adds no syntax or format detail beyond the schema, so the baseline 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?

States a specific verb and resource ('List the citations collected across a project') plus scope (whole project) and ordering ('newest first'). An agent can distinguish it from get-citation-tool purely from the description, and knows it returns citations rather than aggregate analytics.

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?

Usage is implied by the project-scoped framing and the pagination instruction ('follow nextCursor to fetch additional pages'), which is actionable procedural guidance. However, it names no alternative (e.g., get-citation-tool for one citation) and gives no when-not-to-use condition or prerequisite for having a valid project_id.

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