Correlation Subgraph

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

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses important behavioral details: depth expansion is resource-bounded, edge_type pruning changes which nodes are reachable, and min_fidelity uses a scale that '0.5 filters nothing.' It also warns about comparing rounded fidelity and points to raw values, all of which is practical operational behavior.

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 compact and front-loaded with the main purpose, followed by usage guidance and a nuanced numeric validation note. Every sentence earns its place: purpose, budget/expansion rationale, sibling differentiation, and edge-fidelity warning,

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 description is thorough for a graph traversal tool: it covers output shape, expansion pattern, borrowing limits, sibling selection, scale calibration, and edge-specific raw data. With an output schema present and annotations covering safety, it doesn't need to enumerate every return field. It might not describe all edge response capabilities, but nothing essential for invocation is missing enough for a 3.

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 high (86%), so the baseline is decent. The description adds valuable semantics beyond the schema, especially for min_fidelity ('Scale is 0-100, NOT 0-1—typical NPMI edges sit between 5 and 30') and for edge_type pruning semantics. It doesn't add elaborate semantics for every parameter, but the ones it covers are materially helpful.

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 says specifically what the tool does: 'The N-hop neighbourhood around any graph node — nodes, edges, and each edge's fidelity — for incremental exploration of the correlation graph.' This clearly identifies the verb, resource, and output, and it differentiates from get_entity_profile by emphasizing 'actual edge topology.'

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?

The description is explicit about when to use this tool: 'Start at depth 1 and expand' is directly tied to 'a whole-corpus graph exceeds every response budget.' It then names an alternative ('prefer get_entity_profile, which is cheaper') and the condition under which this one should be selected ('when you need the actual edge topology').

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