Assembly Lock Check

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

Beyond the readOnlyHint/openWorldHint annotations, the description explains the logic of each classification, including the subset relationship of interface_changed within modified, what stale means, and the aggregate ok decision. This gives the agent a clear model of the tool's behavior and return semantics.

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 front-loaded opening sentence states the core operation, followed by a tight bullet-like list of categories, the ok rule, and the return object. Every line carries distinct information, and the structure makes the taxonomy easy to scan.

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?

The description thoroughly covers return values and category semantics despite the absence of an output schema. However, with a bare input schema, it leaves important input details unspecified, such as how to supply the manifest and lockfile and the meaning of the lockfile's null default. Adequate overall, but not complete enough to invoke without additional assumptions.

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?

With 0% schema description coverage, the description must compensate. It clarifies that the manifest is the set of current component files and the lockfile is the comparison baseline, but it does not explain the expected string format, what a null lockfile means, or whether manifest is a path or serialized content. Partial semantics are provided, with clear gaps.

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 states a specific action — compare current component files to a lockfile — and enumerates the drift categories it produces. The classification vocabulary (modified, interface_changed, stale, new/removed, ok) makes it distinct from sibling tools like assembly_lock or change_impact.

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 the decision context 'safe to re-merge without re-dispatch', which implies when to use the check. It does not name alternatives or explicitly state when not to use this tool, so it falls short of a full 5.

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