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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered and the description is not required to restate it. What it adds beyond that is genuinely useful: the operation is credit-free, and the result is grouped by conflict type and includes both allowed resolutions and any resolution already applied — which tells the agent whether a second call is needed after mbe_resolve_conflict.

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?

A single compact sentence with the cost note front-loaded, which is the right thing to surface first. The opening "Free." fragment is terse to the point of being slightly cryptic out of context, but nothing in the sentence is wasted.

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?

There is no output schema, so the description must convey the return value — and it does, listing type grouping, allowed resolutions, and existing resolution state. Missing only secondary details such as pagination, empty-result behavior, or required proposal state, which are minor for a one-parameter read tool whose safety profile is fully covered by annotations.

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 0% for the single required proposal_id, so the description must carry the meaning. "A proposal's conflicts" does tie the parameter to a proposal object, but it adds no detail on identifier format, where the id comes from, or behavior when the proposal is unknown.

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?

"A proposal's conflicts grouped by type, with the resolutions each allows and any resolution already made" specifies the resource (conflicts of a proposal) and the exact shape of what comes back, so the agent knows this is a read that returns conflict+resolution data. It does not explicitly name the verb or contrast itself with mbe_resolve_conflict, which is the obvious neighbouring operation, so it stops short of full sibling differentiation.

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?

"Free" is an implicit usage signal (call it without worrying about credit spend, e.g. to inspect conflicts before acting), but there is no explicit when-to-use, no prerequisite state for the proposal, and no pointer to mbe_resolve_conflict as the follow-up action. Usage must be inferred from the name and the returned "resolutions each allows" clause.

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