Record a fix outcome

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

The description clearly discloses the write semantics and the non-idempotency 'each call creates a new fix_attempt, so call once per PR.' It also explains the lifecycle side effects (creates a row, patches it to completed, links it). The annotations already mark write and non-idempotent, but the description adds important context about side effects and safe call frequency, which is beyond what annotations provide.

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 yet succinct, with each sentence serving a distinct purpose: what it records, what it does, its return value, its side-effect/non-idempotency constraint, and the routing to sibling tools. The key warnings are front-loaded after the core function. No extraneous content.

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 includes all necessary information for an agent to decide whether to invoke this tool instead of dispatch_fix or merge_fix, to construct the input meaningfully, and to avoid duplicate submissions. It covers the workflow stage, the side effects, the return value, and the idempotency behavior — everything needed beyond the rich schema and annotation hints.

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?

The schema has full coverage, but the description adds meaning by enumerating the key fields (branch, PR URL, files changed, lines added/removed). Most importantly, it explains the idempotency key's derived fallback behavior, which the schema only describes as 'optional UUID' — the description clarifies that omitting the key still yields a stable key derived from reportId + branch + prUrl, which helps the agent reason about safe retries.

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 verb and resource: 'Record a fix outcome' and 'Creates a fix_attempt row,' clearly distinguishing it from the read-only report tools and other fix-related tools. It explicitly names sibling tools dispatch_fix and merge_fix, which disambiguates it from those alternatives.

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 explicitly says when to use this tool ('Use after you opened a PR outside Mushi') and when to use alternatives ('use dispatch_fix to have Mushi open the PR instead, or merge_fix once CI is green'). This leaves no ambiguity about tool selection.

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