lingam

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

Annotations declare readOnlyHint=true and openWorldHint=false. The description adds substantial behavioral context beyond this: it discloses the validation evidence tier, the statistical assumptions, failure modes (unstable skeleton, many undirected edges), and remedies. It doesn't contradict the annotations. The only minor gap is that it doesn't explicitly state what the output contains, but the output schema exists and the description mentions validation evidence tier. The description adds meaningful behavioral context about when results are trustworthy and what can go wrong.

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 dense but well-organized: it starts with the core action, then validation, assumptions, pre-conditions, failure modes, alternatives, and typical N. Every sentence adds value. It's longer than ideal but the content is substantive and structured with clear labels. It earns a 4 rather than 5 because it's somewhat long and could be tightened, but it's not bloated.

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?

Given the tool's complexity (causal discovery with multiple assumptions and failure modes), the description is remarkably complete. It covers validation evidence, assumptions, pre-conditions, failure modes with remedies, alternatives, and sample size guidance. The output schema exists, so return values don't need to be described. An agent has everything needed to decide whether to call this tool and how to interpret potential issues.

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 100%, so the schema already documents all 7 parameters. The description doesn't add parameter-level detail beyond what the schema provides. It mentions assumptions and data requirements but doesn't map them to specific parameters. Baseline 3 is appropriate since the schema carries the full burden and the description doesn't need to compensate.

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 'Fit DirectLiNGAM (Shimizu 2011)', which is a specific verb and resource. It clearly identifies the algorithm being fit. However, it doesn't explicitly distinguish itself from the sibling tools sp.pc_algorithm, sp.fci, sp.ges, and sp.lingam in the opening; the differentiation is only implicit through the algorithm name and the alternatives list at the end. The name 'lingam' is somewhat generic, but the description clarifies it's DirectLiNGAM specifically.

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 explicit when-to-use guidance: it lists assumptions (Causal Markov, faithfulness, causal sufficiency for PC/GES, FCI relaxes this, acyclicity, linear non-Gaussian model), pre-conditions (i.i.d. observational data for constraint-based methods, environment-labelled data for ICP), and failure modes with remedies. It also names alternatives (sp.pc_algorithm, sp.fci, sp.ges, sp.lingam) and gives a typical minimum N of 500. This is comprehensive usage guidance.

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