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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the description is not the sole source of the safety profile. It adds useful context—conflicts are 'auto resolved by policy or waiting for review'—but is ambiguous about whether the baseline is actually mutated or only a proposal is produced ('merge ... and return the merge proposal'), which matters for a non-idempotent write tool.

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 dense sentence with the key action front-loaded and the cost note first ('Free.'). The long parenthetical enumeration of conflict types is informative but heavy; it earns its place by conveying return content that no output schema provides.

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?

With no output schema, the description usefully enumerates what comes back: every change plus typed conflicts and their resolution state. The main gap is whether reconciliation commits changes to the baseline or yields only a reviewable proposal, which an agent needs in order to call it safely.

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 fragment_id parameter, so the description must compensate. It only indirectly implies the parameter identifies a 'staged fragment'; it gives no format, lookup or validity details, so it adds marginal meaning over the bare 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+resource: merge a staged fragment into the current baseline and return a merge proposal with typed conflicts. It is clearly distinct from siblings like mbe_submit_fragment or mbe_list_conflicts by its merge-and-report role, though it never names those siblings explicitly, so it stops short of a 5.

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 phrase 'staged fragment' implies this is used after a fragment has been submitted, and 'Free' signals no credit cost. There is no explicit when-not guidance or named alternative (e.g., mbe_diff for inspection only, mbe_resolve_conflict for follow-up), so usage must be inferred from the workflow.

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