propose_write

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

No annotations, so the description carries the full burden, and it does well: it discloses that output is staged, returns an op id + diff, and that nothing is written until commit_write. It doesn't cover failure modes (e.g., rewriting a nonexistent path) or auth/model availability requirements, keeping it short of a 5.

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 sentences, front-loaded with the core action, then the return/staging contract, then the usage condition. No wasted words.

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 10-param mutation tool with no output schema, the description covers the workflow contract (staged, op id + diff, commit gate) well. It is slightly thin on the many provider/sampling parameters, but a caller can rely on the schema for those.

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 70%; the description adds no parameter-level detail beyond what the schema already provides. It never explains sampler params, think, options, or provider behavior, so it neither compensates for the uncovered params nor adds meaning over the schema. Baseline 3 is appropriate.

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 action (rewrite/create ONE file), names the local model as the actor, and frames the tool as a staging step. It clearly distinguishes itself from sibling commit_write by stating 'Nothing is written until commit_write' and from propose_edit/propose_write family by scoping to one file.

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 an explicit condition: 'Use for mechanical rewrites where the file content shouldn't flow through your own context.' This tells the agent when this tool is preferable, though it doesn't name the alternative sibling (e.g., propose_edit) or state a when-not case.

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