Request, drive, or list delegated reviews

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

Annotations are minimal (readOnlyHint=false, destructiveHint=false), so the description adds useful context: reviews are pinned to immutable revisions, the lifecycle is guarded, and the tool never modifies a product workspace. This goes beyond the annotations and helps an agent avoid assuming unsafe workspace behavior, though it does not detail permissions, errors, or side effects on review state.

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 carry all the needed high-level information: the core action ('communicate one repository review') and a clear boundary ('never discovers, fetches, checks out, or modifies'). There is no filler, and the description is front-loaded with the tool's primary purpose.

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?

The description plus the well-documented schema (92% coverage) gives an agent enough to form a correct mental model: this is a review communication tool, not a repository or workspace tool, and it follows a lifecycle. It does not explain the review state machine in detail, but the state enum and param annotations carry that part, so the description is sufficiently complete for a tool of this complexity.

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 92% and the per-parameter descriptions in the input schema already explain which parameter belongs to which action. The description adds only high-level context (pinning to immutable revisions, lifecycle actions), not new parameter-level meaning, so the baseline of 3 is appropriate.

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 verb and resource: 'Communicate one repository review pinned to immutable revisions through a guarded lifecycle: request, update, and list.' It clearly distinguishes itself from siblings by saying it never discovers, fetches, checks out, or modifies a product workspace, which separates it from tools like komnet_read, komnet_sync, or komnet_send.

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 implies when to use the tool (for requesting, updating, or listing delegated reviews) and gives exclusions ('never discovers, fetches, checks out, or modifies a product workspace'), which tells the agent what not to use it for. It does not explicitly name alternative sibling tools or give 'instead use X' conditions, so it stops short of full when/when-not guidance.

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