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

No annotations are supplied, so the description carries the whole burden. It does well on payload behavior by spelling out edges (direction, type, evidence) and neighbour papers, and it discloses cost with the '[Free · 1 credit]' tag. It does not state read-only safety explicitly, whether large graphs are truncated or paginated, or how an unknown node_id is handled, leaving meaningful behavioral gaps for a no-annotation tool.

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 payload description is front-loaded in the first clause, followed by the depth escalation rule and the prerequisite chain, with the cost tag last. Every clause carries information; the only mild noise is the cost badge, which is still decision-relevant.

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 and no annotations, the description must explain both how to obtain the required ids and what comes back, and it does both. For a read-only single-node retrieval tool this is close to sufficient; the remaining omissions are edge cases such as invalid ids and response size.

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 67%, so the schema already documents node_id's origin and topic_id's source. The description adds genuine meaning the schema cannot: 'depth 2 adds the neighbours' edges' explains the semantic effect of the depth parameter, which the schema only constrains numerically (min 1, max 2, default 1).

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 names a specific resource (one node of an expert's graph) and enumerates exactly what it returns: edges with direction, type and evidence text, plus neighbours and their papers. That is far more precise than a title restatement. It stops short of differentiating itself from the similarly named library_node_context sibling, so an agent must infer the expert/library split from context.

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 states an explicit prerequisite chain: use this after expert_search_facts / expert_graph_map / expert_communities have supplied a node id. That is real sequencing guidance rather than implied usage. It does not say when to prefer this over library_node_context or when a shallower alternative suffices, so it falls short of full when/when-not coverage.

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