knowledge_check_drift

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It reveals the return data (ADR content + affects_paths) and instructs the agent on subsequent steps, suggesting a read-only operation. However, it does not explicitly state whether the tool has side effects, requires permissions, or any 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 front-loaded with the purpose and clearly structured. It uses bullet-like steps for agent actions without being overly verbose. Each sentence contributes value, though the numbered list could be slightly more concise.

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 tool that simply fetches ADR data for the agent to process, the description is complete. It specifies the return structure, handles the empty affectsPaths edge case, and outlines the expected agent workflow. No output schema exists, but the description adequately covers what the tool provides.

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 input schema has two parameters: 'projectId' (undocumented) and 'adrNumber' (documented as 'ADR number to check'). With schema description coverage at 50%, the tool description adds no extra meaning for 'projectId' and fails to compensate for its lack of documentation.

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 states the tool's purpose: 'Check whether an ADR has drifted from the actual codebase.' It specifies the return (ADR content + affects_paths) and outlines the agent's follow-up actions. However, it does not explicitly differentiate this tool from siblings like knowledge_check_flow or knowledge_check_resolve.

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 no guidance on when to use this tool versus alternatives. It only contains post-call instructions for the agent, such as comparing the ADR to code and returning a drift report, but lacks before-use context or exclusion criteria.

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