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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the bar is lower, yet the description adds real substance: the return is a JSON report with diagnostic codes C000–C095 located by file:line:col plus a budget (warm-up bars, memory, nodes per bar). That is exactly the behavioral/output context annotations cannot convey.

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?

One front-loaded sentence: verb+resource first, then output contract, then the safety/cost note. Every clause carries information; nothing is padding.

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?

No output schema exists, and the description compensates by enumerating what the report contains (diagnostic code range, file:line:col, budget metrics). For a single-parameter, read-only validation tool, nothing an agent needs is missing.

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 100% and the single parameter is fully described there; the description's 'the cubicle.script v1 (the YAML text)' merely restates it. Nothing is added about format edge cases, size limits, or encoding, so the baseline 3 applies.

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 (validate) + specific resource (cubicle.script v1 YAML text) plus the validator it uses ('the reference validator'). 'Nothing runs' implicitly separates it from execution-oriented siblings such as script_rehearse or replay_record, so an agent can route correctly without opening the 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?

'Nothing runs. Free.' gives clear context that this is a safe, cost-free pre-check to prefer before anything that executes or simulates. It stops short of explicitly naming the alternative (script_rehearse) or when-not to use it, so no exclusions are stated.

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