Correlation Subgraph

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds useful budget context (response budgets, depth multiplying node count) which goes beyond annotations. However, it doesn't detail output structure shapes, pagination, or how missing seed entities behave, leaving some behavioral gaps.

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?

A tight 3-sentence description: states the core function, gives the operational strategy, and names the alternative. Every sentence earns its place with zero filler. Front-loaded with the most important information (what it does, how to use it).

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-value documentation is unnecessary. The description effectively covers the purpose, usage strategy, budget warnings, and sibling differentiation. Minor gap: no guidance on which seed_type values are best starting points or max-safe depth given the limit constraints, but the depth=1 recommendation partially addresses this.

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 at 83%, with all 6 parameters documented in the schema (depths, limits, fidelity ranges). The description adds dimension beyond the schema by explaining the 'depth multiplies the node count' cost model and the incremental 'start at depth 1' strategy, which helps the agent reason about parameter choices rather than just their types.

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?

Specific verb+resource: 'The N-hop neighbourhood around any graph node' with explicit scope (nodes, edges, fidelity). Distinguishes from siblings by naming get_entity_profile as the cheaper alternative and clarifying this tool returns edge topology. Clearly differentiates from get_correlation_path and explain_correlation.

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?

Provides explicit when-to-use guidance: 'for incremental exploration', 'start at depth 1 and expand', and a concrete exclusion naming get_entity_profile with reasoning ('cheaper and usually what you want'). Also warns about whole-corpus graphs exceeding response budgets, giving clear usage context.

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