pc_fixer_auto_heal

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

With no annotations supplied, the description carries the full burden, and it discloses the key traits for a mutating tool: it acts autonomously, it takes an automatic backup, it produces an atomic rollback manifest, and dry-run is non-destructive. What it omits is the blast radius (which file classes may be rewritten), permission requirements, and whether failures leave partial edits despite the atomicity claim.

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?

Two tight sentences with no filler, and the safety-relevant behavior (backup, rollback, dry-run) is front-loaded rather than buried. The phrasing 'Safe with dry-run verification mode' is slightly awkward, but every clause carries distinct information.

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 three-parameter mutating tool with no annotations and no output schema, the description covers the essential risk signals an agent needs before invoking it. The remaining gap is relational: it does not say how this fits with pc_fixer_diagnose or pc_fixer_rollback, nor what a successful heal returns, which matters since no output schema exists.

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 path, dry_run, and category are already documented, and the description only reinforces dry_run via 'dry-run verification mode'. It adds no meaning for path or category, and notably does not clarify category values beyond what the vague 'e.g.' list in the schema offers, so the baseline 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?

The description uses a specific verb (heal) on a specific resource (codebase and environment defects) and adds distinguishing mechanics: automatic backup plus an atomic rollback manifest. It never names the sibling tools (diagnose, rollback, check_system) or explicitly contrasts itself with them, so an agent must infer that this is the mutating counterpart to pc_fixer_diagnose.

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?

'Safe with dry-run verification mode' implies a recommended workflow of trying dry_run before applying, which is genuinely useful guidance. However, it states no explicit when-to-use versus pc_fixer_diagnose (detection) or pc_fixer_rollback (recovery), and gives no prerequisite such as running a diagnosis first.

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