Repository Harness

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

The annotations declare readOnlyHint: true, so the description does not need to repeat that. It adds a behavioral detail: it can generate different types of commands (setup, validation, runtime, context) and can optionally return a markdown report (via includeMarkdown) or full JSON. This goes beyond what annotations provide, clarifying the output format options and the scope of generated content.

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 one sentence, concise and clear, with the verb first ('Generate') and the main part stated upfront. It efficiently conveys the purpose without unnecessary words. It could be slightly improved by mentioning the markdown option in the description for completeness, but it is already moderately concise and well-structured.

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 read-only tool with no required parameters and a 100% schema description coverage, the description covers the essential purpose and basic behavior. It does not mention return values, but since there's no output schema and the schema covers parameters, the description is sufficient for an agent to understand what the tool does. The lack of detail on how to use the output (e.g., how to interpret the generated commands) is a minor gap.

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 both parameters adequately. The description does not add semantic detail beyond what the schema provides—e.g., it doesn't explain how 'path' might affect command generation or what 'includeMarkdown' changes in detail. Given the high coverage, a score of 3 is appropriate as a baseline.

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 states a specific verb ('Generate') and a set of resources ('setup, validation, runtime, and context commands'), which clearly identifies the tool's purpose. However, it does not explicitly differentiate it from sibling tools like 'context_pack' or 'workspace_report', which might also generate context-related outputs. The phrase 'for an agent or CI harness' adds useful context but does not distinguish between the tool and its siblings.

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 implies usage in the context of an agent or CI harness (when you need to generate commands), but it does not explicitly state when to use this tool versus alternatives like 'repo_inspect' or 'context_pack'. There is no mention of conditions or exclusions. The phrasing 'Generate ... commands' gives a hint that it's for command generation, but without explicit guidance, an agent might struggle to select the right tool among siblings.

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