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

Annotations already cover read-only/idempotent/non-destructive behavior, and the description adds contextual grounding: the returned content is a cached artifact rather than a live repository scan and is 'verify-before-trusting' guidance. This helps set an agent's expectations about staleness and reliability beyond what the annotation flags alone communicate.

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?

Four short sentences with four distinct jobs: when to call, what it returns, when to skip and the parameter contract. The uppercase 'CALL' opening front-loads the most important trigger condition and no sentence is wasted.

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 100% schema parameter coverage, an output schema, and strong annotations, the essential decision information is present. The missing analyze_repo route contrast is the main gap, while the cached/verify guidance and output schema fill most of the remaining behavior.

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?

Parameter description coverage is 100%: the schema fully explains repo, format, and package, including example formats and the versioned-return alternative. The only new semantic in the description is 'exactly one of repo or package', which re-states what the schema's oneOf already enforces.

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 names a specific verb and resource: it 'CALLs' to return the cached CLAUDE.md-style artifact or Cursor rules for orienting an agent in an unfamiliar repository. The title reinforces the distinct purpose ('Orient an agent in an unfamiliar repository'), and the description's focus on orientation artifact distinguishes it from version-judgment and risk-analysis siblings, though it does not explicitly separate it from analyze_repo.

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?

When to call is explicit ('CALL before substantial code work in an unfamiliar repository') and the 'do not call again if the artifact is already in context' condition is a clearly stated idempotency guard. The package schema also points to evaluate_dependency_change for version-specific judgments, providing a named alternative. However, the description does not explain when to choose this over the heavily overlapping analyze_repo sibling.

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