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

Annotations declare destructiveHint=true but not what dies; the description spells it out — the losing side's content is overwritten — and adds non-obvious timing semantics (the choice is recorded now and applied on the next sync, which converges both sides and clears the conflict). That is real information an agent cannot get from the structured fields.

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?

Front-loads the core action and then layers semantics, timing, and the diff prerequisite in tight order. The final recommendation sentence is slightly advisory but still earns its place; 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?

Covers action, both resolution outcomes, the deferred application on next sync, the destructive consequence, and the recommended pre-step. With no output schema, it still tells the agent what state change to expect, leaving nothing material unstated.

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 baseline is 3, but the description adds genuine meaning for the enum by defining what each value does ('git' updates the cluster record to match Git; 'cluster' pushes the cluster version back to Git). cluster_id scoping and resource_key format are left to the schema.

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 verb and resource ('Resolve one GitOps merge conflict by picking the winning side') and immediately differentiates itself from siblings list_gitops_conflicts and get_gitops_conflict_diff by describing a mutation rather than a read.

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 a clear prerequisite workflow: inspect the diff with get_gitops_conflict_diff and state the recommended side before calling. It names a sibling tool and the condition for using it, though it never says when a conflict should not be resolved this way.

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