Dispatch Mushi fix agent

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

Annotations already provide readOnlyHint=false, idempotentHint=false. Description adds concrete side effects (writes branch, opens signed draft PR) and confirms non-idempotency, adding value beyond 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?

Every sentence serves a purpose: action, configuration, prerequisites, return value, next steps, classification requirement. Front-loaded with core functionality. No redundancy or 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?

Covers prerequisites, return format, classification condition, and links to sibling tools for subsequent steps. Lacks error handling or rate limit info, but overall sufficient given the complexity and sibling context.

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 has 100% coverage with clear descriptions for all parameters. Description adds useful detail for agent parameter (specific values and default behavior) and reinforces idempotency semantics, but does not elaborate on reportId or inventoryActionNodeId beyond schema. Adequate but not compensatory.

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?

Clear verb-resource pair: starts a fix agent for a classified report, writes branch, opens draft PR. Distinguishes from siblings by specifying prerequisite (triage_issue) and post-actions (get_fix_timeline, merge_fix).

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?

Explicitly states prerequisites (GitHub connected, LLM key, run diagnose_setup first) and when to use alternative tool (triage_issue if report not classified). Also guides subsequent tool use (poll timeline, merge when CI green). Could be improved by mentioning when NOT to use.

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