resolve_project

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

The description explicitly states the tool is read-only and does not create directories or mutate state, which is critical behavioral info. With no annotations, this transparency is high, though it doesn't detail error handling for missing files.

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?

Two sentences: first states the action and result, second clarifies read-only nature. No redundancy, fully front-loaded, every word adds value.

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 no output schema, the description lists all return fields. It covers inputs, behavior, and non-mutating nature. Missing error conditions (e.g., missing cq.yaml) but sufficient for typical usage.

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%, so baseline is 3. The description adds minimal extra context beyond the schema's parameter descriptions, which are already detailed enough. No significant new semantics are introduced.

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?

Description clearly states the tool resolves cq.yaml and CQ_CONFIG_JSON into a ResolvedConfig view, listing specific return fields. The verb 'resolve' and resource 'config' are concrete, and it distinguishes itself from siblings like 'validate_project' and 'inspect_project' by focusing on resolution.

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 use when a resolved config view is needed but does not explicitly state when to use over alternatives like 'validate_project' or 'inspect_project'. No when-not-to-use or exclusion criteria are provided.

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