Classify Coding Task Route

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds useful semantic context about local-supervised and the mandatory full-diff Claude review, but it does not describe the tool's own output behavior or other classification criteria in a way that goes substantially beyond the annotations.

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?

Two compact sentences with no filler. The category list is front-loaded, and the key term local-supervised is immediately clarified with a consequential constraint. Every sentence earns its place.

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?

There is no output schema, so the description should explain what the tool returns or how the classification is expressed, but it does not. Only one of the four categories is defined, leaving deterministic, local, and Claude ambiguous. With 8 parameters, 13% schema coverage, and many related sibling tools, the description is not complete enough for reliable 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 only 13%, so the description carries most of the burden for explaining the 8 parameters. It does not explain task, riskTags, solutionKnown, estimatedFiles, validationKnown, requiresDiscovery, requiresArchitecture, or sensitiveDecisionResolved. The description only indirectly relates to sensitiveDecisionResolved through the local-supervised definition, which is insufficient for an agent to set parameters correctly.

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 categorizes a coding task as deterministic, local, local-supervised, or Claude, and it defines the local-supervised category. It does not explicitly differentiate itself from the sibling execution tools, but its role as a classifier is evident from the title and categories.

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 this tool is a routing/classification step for local code tasks and explains when local-supervised applies, but it never explicitly says when to use this tool versus execute_local_code_task, delegate_code_task, or other siblings. The 'full-diff Claude review is mandatory' note provides some routing consequence, but no direct when/when-not guidance.

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