Dispatch Mushi fix agent

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

Annotations already show readOnlyHint=false and idempotentHint=false, and the description reinforces these by stating it writes a branch, opens a PR, and that each call without the idempotency key creates a new attempt. It adds dependencies (GitHub + LLM key), idempotency behavior, and operation semantics that are not available from annotations alone.

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 but well organized: behavior first, then configuration, prerequisites, return value, polling guidance, idempotency, and a precondition. Every sentence carries workflow-relevant information and there is no redundant filler.

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?

Given the four parameters and the tool's broader workflow, the description covers behavior, prerequisites, idempotency, returns, and follow-up actions. The remaining details like inventoryActionNodeId are already thoroughly documented in the input schema, so no critical decision context is missing.

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 coverage for parameter descriptions is 100%, so the baseline is 3. The description adds useful meaning about the agent selection and idempotency key usage, but it also instructs callers to set agent="cursor_cloud", which is not present in the schema enum (claude_code, codex, rest_worker, mcp). That mismatch could cause an agent to select an invalid value and sizes the otherwise strong guidance.

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 names a specific verb-resource pair ('Start a Mushi fix agent'), targets a classified report, and states concrete effects: writes a branch and opens a signed draft PR. It clearly distinguishes this dispatch action from the many get_* and merge_fix sibling tools.

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?

It explicitly says when the tool is appropriate (classified report), what prerequisites apply (GitHub connected + LLM key, run diagnose_setup first), and what to do before or instead (run triage_issue if report isn't classified). It also gives the follow-up workflow: poll get_fix_timeline and then merge_fix when CI is green.

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