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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds meaningful behavioral context beyond annotations: the script sends nothing unless --send is used, requires user agreement, and native members are unsupported. This is useful safety-relevant disclosure not available in annotations.

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 mostly purposeful, with the core purpose front-loaded. The second sentence is long and combines instructions with script behavior, making it slightly harder to parse, but every clause carries relevant information.

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 output schema, the description covers what is returned (script, plan, conformance suites), how to use it (write to scratch, run node command), what the script reports (counts and versions only), and safety behavior (--send). It does not describe exact file names or response structure, but it gives enough context for the agent to proceed.

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 0%, but the description helps by specifying that the members must be 'exact source members from compat_check', adding provenance and resolution semantics beyond the raw id/version schema. The single parameter's structure is already fully documented in the schema, so the description's semantic constraint compensates well.

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 a specific verb and resource: 'Return the files of the local verify step for exact source members from compat_check.' It clearly names the artifact types (script, plan, conformance suites) and distinguishes this from generic compat_check by emphasizing the local verify step.

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 clear context by tying the tool to 'exact source members from compat_check' and gives an explicit exclusion ('Native members cannot be verified locally'). It lacks explicit alternative tool names, but the condition and restriction are enough to guide selection.

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