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

Annotations already declare a safe read (readOnly, non-destructive), yet the description adds substantial context beyond them: exactly what is returned (releases, clean changes, conflicts with base/ours/theirs), the resolution contract, and the meaning of adoptMode and upToDate edge cases.

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-loaded with the core purpose, then the return shape, then the resolution contract. The prose is dense and long but most sentences carry distinct operational content; it could be trimmed but nothing is clearly redundant.

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 carries the full burden and does so: it enumerates return fields (releases, added/changed/removed paths, conflict base/ours/theirs contents) and covers both adoptMode and upToDate terminal states.

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 0% and the description never explains flowId, so it does not fully compensate for the gap. However flowId is self-evident from the tool's name and sibling conventions, keeping this at a baseline adequacy rather than a failure.

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 clearly: 'Review what an update from the original build would change,' framed as a read operation 'shaped for an agent.' It is readily distinguishable from the sibling apply_upstream_update (which it routes to) and flow_get_upstream_status.

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 strong next-step guidance ('Then call apply_upstream_update with exactly one resolution per conflict') and explains branch conditions via adoptMode and upToDate. It does not explicitly contrast with flow_get_upstream_status, but the when-to-use context is otherwise clear.

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