Propose a recipe change (draft PR)

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

Annotations only say openWorld=true, idempotent=false, destructive=false. The description adds the safety model that matters: the PR stays a draft so repo CI does not run, nothing is merged or published, baseSha pinning prevents reverting someone else's edit, and malformed content (mushi.recipe.json, the inventory) is rejected.

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 lead sentence front-loads purpose and output (draft PR), and nearly every clause carries operational meaning. It is a dense run-on paragraph with heavy parentheticals, so it is slightly harder to scan than it could be.

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?

No output schema exists, yet the description names both return shapes ({ dryRun, files, denied } and { jobId, status, prUrl }), covers prerequisite (user confirmation), versioning (baseSha), and validation failures. Nothing needed to call it correctly 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?

With 60% schema coverage, the description compensates by mapping element/edits to concrete recipe surfaces (design tokens, budgets, .env.example, store listing text) and explaining the baseSha round-trip and confirm semantics. It does not touch title or projectId, so it is strong but not exhaustive over all five parameters.

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?

States a specific verb+resource (propose edits to recipe-allowed files as ONE draft pull request) and enumerates the exact scope: design tokens, mushi.recipe.json budgets, .env.example, store.listingDir. An agent can distinguish it from siblings like propose_portfolio_change or get_recipe_change without opening a schema.

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?

Gives explicit when-behavior (dry run by default) and when-not (confirm is refused if a file changed since the dry run; confirm: true requires user confirmation first). It also specifies what is never writable (workflows, env files, lockfiles, generated exports, migrations), making the boundary unambiguous.

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