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

With no annotations provided, the description fully discloses the tool's behavior: re-fetching, comparing hashes, re-running planner, and reporting drifts. It implies a read-only operation (no mutations), though it doesn't mention permissions or rate limits.

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 two sentences with no wasted words. The first sentence lists specific actions, and the second provides an analogy. It is front-loaded with the core purpose.

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 a single parameter and no output schema, the description adequately explains the tool's functionality and what the user can expect (drift reports with moved fields). Minor omission: exact output format is not described, but the description suffices.

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?

The sole parameter 'artifact' is described in the input schema with a clear explanation: the JSON object or string from kcp_plan. The tool description adds context but does not significantly extend meaning beyond the schema.

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 clearly defines the tool's action: cross-examine a saved plan artifact by re-fetching manifests, comparing sha256, re-running the planner, and reporting drifts. It distinguishes from siblings like kcp_plan (which creates plans) and kcp_validate (which might validate other aspects) by focusing on replaying an existing plan.

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 after obtaining a plan artifact from kcp_plan, and positions it as a verification step. However, it does not explicitly state when not to use it or directly contrast with sibling tools.

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