propose_revision

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

No annotations are provided, so the description carries the safety burden; it explicitly discloses that the revision is not saved and details three validation checks (fingerprint, protected passages, style heuristics). It does not mention error behavior or return format, but the side-effect profile is clearly stated.

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?

One front-loaded sentence communicates purpose, side-effect, and validation criteria with no filler. The semicolon cleanly separates the primary action from the behavioral details.

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 tool with no annotations and no output schema, the description covers purpose and behavior but leaves return shape, failure modes, and exact parameter requirements unstated. This is adequate but has clear gaps.

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 descriptions are absent (0% coverage), but the description maps 'current fingerprint' to base_sha256 and 'proposed rewrite' to revised_content, giving useful context. It does not explain slug or optional change_summary, and it omits format/constraint details, so the compensation is partial.

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 ('validate') and identifies the resource ('proposed rewrite'), explicitly noting it does not save. The phrase 'checks the current fingerprint, protected passages, and style heuristics' adds concrete scope that distinguishes it from sibling apply/approve tools.

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?

'Without saving it' clearly frames the tool as a dry-run validation step, so an agent can infer using it before apply_revision/approve_revision. It does not explicitly name alternatives or exclusions, but the context is clear enough relative to the sibling names.

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