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

Goes well past the readOnly/idempotent annotations by disclosing exactly which defects are reported, that a clean tree additionally yields the root expected value, and that it refuses unreadable trees (unknown parent, loop, two roots, over limits) with the offending line or id named. That refusal/error behavior is the kind of thing annotations cannot express.

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?

Front-loaded with the when-to-use trigger and examples, then the return payload, then refusals, then exclusions — a sensible order. The middle sentence is a long semicolon-delimited enumeration of checks that is dense but each item is a distinct diagnostic, so little is truly filler.

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?

For a validating tool with 3 optional params, the description covers triggers, accepted inputs, every reported defect category, the clean-case extra output, and hard failure modes. Even though an output schema exists, the enumeration of diagnostics makes the result shape predictable before calling.

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%, including a full outline grammar and worked example, so the description's input discussion is largely a pointer to parity with make_decision_tree rather than new semantics. The only added meaning is that both outline and node list forms are accepted here just as in the sibling, which is useful but modest.

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?

States a specific verb and resource ("checked" / "decision tree") and immediately scopes it as validation-only ("without a drawing"). It explicitly contrasts with make_decision_tree by saying it takes the same input but does not draw or create files, so an agent can distinguish the two without reading either schema.

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?

Gives concrete trigger phrasing the user might say ("do my probabilities add up to 1", "is anything missing in this tree") plus an explicit exclusion: "Do not use it to estimate probabilities" and "Does not draw the tree or make files." The alternative sibling is named and the relationship (same inputs, different output) is spelled out.

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