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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuine context beyond that: results mix explicit links with derived co-occurrence, each edge carries distinct-record counts and cited evidence, and pagination consistency requires pinning snapshot_id. That is meaningful behavioral disclosure for a read 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?

Three dense clauses with zero filler, front-loaded with the core result shape followed by the two behavioural levers (filtering, paging). Every sentence carries information an agent needs; nothing restates the name or annotations.

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 an output schema present, return values need not be described, and the description instead covers the graph construction, filtering semantics, and pagination invariants. For an 8-parameter tool the only real omission is any characterization of the offset parameter, which is undocumented in both description and schema.

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 only 38%, so the description must compensate, and it does: it explains types (pre-filter on neighbours, applied before bounds), edge_id (pages that edge's evidence), snapshot_id (pin for stable paging), and implies seed ('from a typed ID'). limit, max_edges and max_nodes are documented in-schema; only offset remains unexplained anywhere.

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+resource: 'One-hop graph from a typed ID', and elaborates the two link classes (explicit catalogue links, derived co-occurrence) and what they carry (distinct-record counts, cited evidence). An agent knows exactly what it gets. It does not, however, name or contrast with the closest sibling, find_related, which also returns related entities.

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?

'types filters neighbours before the bounds' and 'Pass edge_id to page its evidence; pin snapshot_id across pages' give real operational guidance on filtering and paging. But there is no when-to-use vs alternatives statement, and no exclusion regarding find_related or list_cluster_partners, so usage is only implied for the discovery-vs-graph decision.

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