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

Annotations only declare readOnlyHint and openWorldHint, so the description must add behavioral detail, and it does: it discloses that results are normalized with canonical seeds and source provenance, and that partial results signal indexed-coverage or candidate-window limits. This is useful operational context beyond the safety hints.

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 sentences front-load the purpose before invocation details and partial-result behavior. The phrasing 'normalized nodes, canonical seeds and source provenance' is somewhat dense jargon, but each sentence carries distinct information.

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 cursor-paginated graph-traversal tool with an output schema already documenting return values, the description covers the seed inputs, mode direction, continuation semantics and partial-result caveats. It omits any note about the unsupported intent parameter beyond the schema, but that is minor.

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 baseline is 3. The description restates the mode choice (references/citers), the 1-10 seed count and the cursor/limit continuation rule, which largely duplicates the schema descriptions rather than adding new syntax or format guidance.

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 (Retrieve) and precise resource (one-hop paper citation edges) with a named source (Europe PMC). It is clearly distinguishable from siblings like search_papers, inspect_paper and read_paper, since it describes graph-edge retrieval rather than search or full-text reading.

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?

Explains how to invoke it: supply 1-10 seed identifiers and choose references for outgoing edges or citers for incoming edges, then continue with cursor plus optional limit. It gives clear operational context but never explicitly contrasts itself against sibling tools, so it stops short of naming when to prefer it over search_papers.

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