runrunit_commit_per_file

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

With no annotations, the description carries the full behavioral burden and largely succeeds: it discloses the safe default (plan, no git mutation), the secret-filtering behavior, the side-effect boundary (does not open a PR), and the routing hint for next_tool. These are exactly the safety and state-change facts an agent needs before invoking a git-writing tool.

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?

Four short sentences with the purpose front-loaded, then the plan/execute rule, then scope boundaries. Every sentence contributes new information with no filler or repetition of the schema.

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 multi-parameter git-writing tool with no annotations and no output schema, the description covers the critical behavior: default mode, execution trigger, secret handling, and PR boundary. The one gap is the shape/content of the returned plan, which is only described as "a plan" rather than what the agent should inspect before approving.

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 description coverage is 100%, so the schema already documents all eight parameters, including the plan/execute semantics of approved and the as-is handling of commits. The description reinforces a couple of these but adds no syntax, format, or constraint details beyond what the schema provides, so the baseline of 3 applies.

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 and resource ("Plans one commit per changed file, in dependency order") plus the exact subject format and secret exclusion. This is immediately distinguishable from siblings like runrunit_format_commit_message and runrunit_create_pr_github, since it explicitly says it does not open a pull request.

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?

Explains the two-phase flow precisely: default is plan-only, and execution requires passing approved:true with the same commits list. It also names the follow-on tool conditionally ("If includes_pr is true, next_tool is runrunit_check_pr"), so the agent knows how to sequence this against other tools.

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