athena_pag_candidate_discover

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

No annotations are provided, so the description carries the burden. It discloses boundedness, reliance on Gaussian conditional independences, conservative collider propagation, and the fact it is not full FCI/RFCI. However, it does not describe output format, whether it mutates state, or potential failure modes.

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 convey the core function, method, and limitation without fluff. The description is front-loaded with the primary action and resource, making it easy to scan.

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?

Despite the clear purpose, the description is incomplete for an agent: there is no output schema, no annotations, no return-value explanation, and the four parameters are undocumented. For a non-trivial causal discovery operation, this leaves significant gaps in using the tool correctly.

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 for parameter meanings. It indirectly references 'samples' via 'observed Gaussian conditional independences' and hints at boundedness with 'bounded', but it does not explain alpha, variables, or max_conditioning values. This is insufficient for a 4-parameter tool with no schema descriptions.

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 uses a specific verb ('Build') and names the exact resource ('a bounded PAG-like circle/arrow/tail candidate') derived from a defined method (Gaussian conditional independences and conservative collider propagation). It explicitly distinguishes itself from full FCI/RFCI, clarifying scope.

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 provides a clear exclusion ('Not full FCI/RFCI') but does not explicitly state when to use this tool over sibling causal discovery tools like athena_causal_skeleton_discover or athena_pc_stable_discover. The intended use is implied rather than directly stated.

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