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

With no annotations, the description carries the transparency burden. It explains the exact returned graph structure (nodes with title, series, working group, reference counts; edges with source, target, reference type, count) and parameter constraints (depth 1-3, optional reference_type). It does not mention error cases or rate limits, but the read-only nature is evident from 'Get' and 'Returns JSON'.

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 concise (around 120 words), front-loaded with a clear one-sentence purpose, then structured return details and Args. Each line adds useful information without repetition or filler.

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?

The tool has 3 parameters and an output schema, and the description covers parameter semantics and return fields. However, it does not provide usage context relative to sibling tools or mention potential edge cases (e.g., missing spec_number, depth limit behavior). This is a minor gap, so not a perfect 5.

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?

The JSON schema only provides types and defaults, so schema description coverage is 0%. The description's Args section adds full semantics: spec_number as center, depth as number of hops with valid range/default, reference_type as filter with allowed values. This fully compensates for the schema gap.

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 and resource: 'Get a relationship graph centered on a specification, expanding N hops.' It clarifies the graph traversal nature and distinguishes it from sibling tools like get_spec_references or get_spec_dependents by highlighting multi-hop expansion and node/edge output.

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?

There is no explicit comparison to alternatives or exclusions. The phrase 'expanding N hops' implies use for relationship graph exploration rather than direct reference lookup, but the description does not state when to prefer this tool over get_spec_references or get_rfc_lineage. This is implied usage, not explicit guidance.

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