propose_conflict_resolution

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

With no annotations provided, the description is the only source of behavioral disclosure. It does convey the primary side effect: creating a new, independently reviewable Change Request linked to the original conflict. However, it does not disclose whether the original change request is modified, finalized, or left untouched, nor does it describe the relationship between the new CR and the original beyond being linked.

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 sentences, both relevant and front-loaded. The first states the action, mechanism, and prerequisite; the second clarifies the key outcome. No repetition of schema fields or other 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 tool with 3 required parameters and no output schema, the description provides enough to call it: what to pass, where the commits live, and what the result is. The main omission is how the original conflict's state is affected and whether the returned information is a new change ID or some other confirmation, but the overall context is still reasonable.

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?

The schema has 0% description coverage, so the description must carry the semantic weight. It clarifies the meaning of resolver_workspace_id ('separate resolver workspace'), implicitly ties change_id to the original conflicted Change Request, and leaves rationale quite generic. Parameter names are self-explanatory, but the description does not fill in all details for an agent about what to pass as rationale or how to locate the original change from change_id.

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 states a specific action ('Propose a resolution'), names the target resource ('conflicted Change Request'), and explains the mechanism ('using commits already made in a separate resolver workspace'). It also distinguishes itself from the sibling apply_conflict_resolution by explicitly noting it 'creates a new, independently reviewable Change Request linked to the original conflict.'

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?

The description establishes a clear usage context: this tool is for when commits have already been made in a separate resolver workspace. The mention of 'separate resolver workspace' implies preparation steps and clarifies that resolution is proposed rather than directly applied. It does not explicitly contrast with apply_conflict_resolution, but the intent is fairly evident.

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