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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that pagination is cursor-based, that a page's count is page-local not work-global, that unresolved references are split out, that it accepts both uuid and arXiv ids, and that it is deterministic with no model call. This is rich behavioral context beyond what the schema shows.

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 dense but every sentence earns its place: it defines the two directions, explains the pagination model, warns about page-local counts, notes accepted id formats, and states determinism. It is front-loaded with the core purpose and then layers usage-critical details. No filler or repetition of schema content.

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?

For a tool with 5 parameters, no output schema, and no annotations, the description covers all the essential operational knowledge: direction semantics, pagination mechanics, id formats, run attribution, and determinism. The only minor gap is that it doesn't describe the exact shape of the returned page, but the pagination explanation and the absence of an output schema make this acceptable.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining the semantic difference between the two direction values ('who has built on this work' vs 'what this work builds on') and by clarifying that 'after' is a cursor from a previous page's next_cursor. It also explains the run_id attribution semantics, which the schema only partially covers. It doesn't add much on 'document' or 'limit', but the schema already covers those.

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 states a specific verb ('answers') and resource ('citation network around a document'), and explicitly distinguishes the two directions: 'cited_by' for who cites the work and 'cites' for what it references. It also differentiates from siblings by framing this as the entry point to an unread neighbourhood, which is a clear conceptual niche.

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 gives explicit when-to-use guidance: 'cited_by' is the entry point to a neighbourhood you have not read, and 'cites' is for what the work builds on. It also explains the pagination protocol (cursor-based, not offset) and the run_id attribution requirement, which are critical usage conditions. No alternatives are named, but the direction-specific guidance is strong enough to route an agent.

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