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

Annotations already declare readOnly/idempotent/openWorld, so the description is free to add genuinely new behavior: the algorithm changes at the 15-seed threshold, seeds are excluded from results, scores are only comparable within a single result set, and unresolved seeds appear in diagnostics. These are non-obvious traits an agent could not derive from annotations or schema.

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?

It is front-loaded with purpose and input contract, and nearly every sentence carries information. The middle technical run ('Adamic/Adar plus Salton co-citation on a depth-1 citation graph') is dense jargon in a single unbroken paragraph, which slightly hurts scanability.

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?

Output schema exists, so return values need no explanation, and this is a read-only tool with annotation coverage. The description covers input format, algorithm-dependent behavior, scoring comparability caveats, and error surfacing via diagnostics - nothing an agent needs to call it correctly 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 coverage is only 50%, and the description compensates well: it explains the 2-15 reciprocal-rank merge versus the synthetic-paper approach above 15, which materially changes how seeds should be chosen, and it restates the limit ceiling. The 50% gap is the undocumented limit default, which is low-impact.

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 opens with a specific verb+resource and mechanism: 'Ranks papers by their citation links to the seeds, which surfaces related work that keyword search misses.' That last clause explicitly distinguishes it from keyword-based siblings such as search_literature, so an agent can pick it 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?

It establishes the triggering condition (you have seed papers; you want related work keyword search misses) and the input contract of 1-500 seeds. It does not name or route to concrete alternatives among connect_papers, explore_citation_network, or query_citation_graph, so the agent must infer which citation tool to prefer.

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