athena_causal_skeleton_discover

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

With no annotations, the description carries the full burden. It discloses that it's heuristic and for hypothesis generation only, but fails to mention output format, side effects, determinism, or data assumptions. The description adds some behavioral context but not enough for a complex computational tool, though 'discover' suggests a read-only computation.

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?

Two sentences, immediately states the core action and scope. No filler or redundant content.

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 annotations and no output schema, the description leaves out return value expectations and data requirements. It covers the algorithm's nature and scope but is insufficient for a causal discovery tool with nuanced parameters.

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 0%, so the description must compensate. It indirectly explains 'max_conditioning' and 'association_threshold' via 'marginal/one-variable partial-correlation thresholds', but does not define 'samples' or 'variables' beyond what the schema shows. Partial compensation but incomplete.

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?

Clearly states verb 'Generate' and specific outcome: 'heuristic observational association skeleton and candidate v-structures'. Differentiates from siblings by explicitly noting 'marginal/one-variable partial-correlation thresholds' and 'Hypothesis generation only', which indicates a simplified exploratory algorithm distinct from full PC/FCI/PAG discovery.

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 clear context that this is for hypothesis generation only, implying it should be used early in analysis and not for confirmatory causal estimates. However, it does not explicitly name alternative tools or state when not to use it beyond 'only'.

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