Delegate Read-only Code Task to Local Model

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's 'without modifying repository files' reinforces rather than adds behavior. It does contribute the useful detail that this delegates to a 'fast local model' and returns 'bounded' text, but does not explain output size, response structure, or failure behavior.

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?

One sentence, front-loaded with the core action and read-only guarantee, with no wasted words. It is concise and easy to parse, though the brevity contributes to the parameter-semantics gap.

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 with no output schema, 0% parameter coverage, and several closely related siblings, a single sentence is not enough. The description covers purpose and safety, but omits how the response is shaped, how output/context/language/constraints interact, and when the read-only delegation should be preferred over alternatives.

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 schema description coverage at 0% and five parameters, the description was expected to compensate, but it offers no per-parameter guidance. Words like 'code/analysis' hint at the output enum and 'bounded' hints at constraints, but task, context, language, and constraints are left entirely to the agent's inference from names alone.

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 ('Ask the fast local model') and a clear outcome ('bounded code/analysis text') while explicitly noting it does not modify repository files. This distinguishes it from execution-oriented siblings like execute_local_code_task, though it could be even sharper about what 'bounded text' means.

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 phrase 'without modifying repository files' implicitly signals this is the read-only counterpart to execution tools, but it does not explicitly state when to choose this tool over local_coder_health, classify_local_code_task, or execute_local_code_* variants. Usage context is present but mostly inferred.

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