Repair safe .riv lint findings

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

With no annotations, the description carries the burden and does real work: it discloses the per-change pixel comparison, that visual changes are skipped with reasons, that the result is validated before writing, and that dryRun never writes. This is substantive safety/behavior context beyond a bare 'repair' verb; only failure modes and what the validation report contains are left open.

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?

Three short sentences, each carrying distinct information (procedure, per-change policy, dryRun guarantee), with the core action front-loaded. No 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?

For a 4-param mutation tool with no annotations and no output schema, the description covers process, safety of writes, and dryRun behavior well. It stops short of describing the returned result or how skipped changes are reported, which an agent calling it blind might want.

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 is 100%, so the schema already documents path, out, fixes, and dryRun, including the 'source is never overwritten' guarantee. The description reinforces dryRun semantics ('dryRun never writes') but adds no syntax, defaults, or interaction details beyond the schema — baseline 3.

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 and resource — 'Repair lint findings' — and scopes it to 'one change at a time', which separates it from the detection-side sibling riv_lint. It never names a sibling explicitly, so the differentiation is implicit rather than stated.

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?

Usage is implied (run after lint, one fix at a time, skip visual changes) but there is no explicit 'use this when / use riv_edit or riv_optimize instead' routing. An agent must infer the position in the workflow from the mention of 'lint findings'.

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