Check brain cards against the repo's real files (drift report)

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

Beyond the annotations (idempotent, non-destructive, not open-world), the description meaningfully expands behavioral transparency: it explicitly says 'Nothing is written,' explains that a 'missing' file may simply be absent from the current checkout, covers rename-candidate detection, and clarifies that slash-joined enumerations and other-project paths are skipped. This gives the agent nuanced expectations beyond the structured hints.

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 dense and front-loaded with the core 'Read-only drift check' intent. Every sentence carries useful behavioral information, but the writing is somewhat verbose, especially around the branch divergence explanation and the 'fix cards' note. It is well-structured for a complex tool but not maximally 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?

Without an output schema, the description does a good job explaining what the tool reports: missing/moved files, rename candidates, and branch divergence status. It also covers edge cases like other-project paths and checkout-local absence. The main gap is the lack of explicit detail about the return format or how the report is delivered, but the description covers the essential context for correct invocation.

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 baseline is 3. The description does not add significant parameter-level detail beyond what the schema already provides; it only restates the default behavior contextually. Since the schema already documents both optional parameters and their defaults, no additional compensation is needed.

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 opens with 'Read-only drift check' and precisely defines the operation: verify brain card file references against the working tree and report missing/moved files plus branch divergence. This clearly identifies the tool's resource and purpose, and differentiates it from sibling tools like project_map_scan or brain_reconcile by focusing on drift detection rather than scanning or reasoning.

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 strongly implies when to use the tool—when you need to check whether brain card file references are still valid in the repo—but it does not explicitly state when not to use it or name alternative tools. Sibling context suggests related tools exist, but no direct comparison or exclusion is provided, so usage guidance is implied rather than explicit.

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