invariance_review_claim

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

The description goes beyond the annotations by specifying that the review's status becomes 'claimed' and that this prevents other agents from picking it up, the calling agent is thereby tied to the claim. It stops short of describing failure cases such as when the review is already claimed or whether permission/ownership constraints apply, but the core mutation is fully transparent.

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 with no filler: the first sentence tells what the tool does and its side effect, the second handles lifecycle. The purpose and state effect are front-loaded, and the sibling references are compact. A small amount of detail about failure cases could be added without bloat.

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?

For a simple two-parameter claim operation, the main intent and effect are covered. However, since there is no output schema, the description does not mention what the tool returns, nor does it cover edgecases such as already-claimed reviews, non-pending reviews, or concurrency conflicts. It is enough to make the correct call in the common case, but not fully complete.

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?

The schema only describes notes, not the required id, and the description doesn't explicitly map id to the pending review it mentions. The phrase 'claim a pending review' makes the intent of the id inferable, but the description does not directly reinforce its meaning, format, or required identity. The id's semantics are under-specified relative to the 50% schema coverage.

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 uses a specific verb ('claim'), names the resource ('pending review'), and states the concrete effect ('sets status to claimed'). It also explicitly names the sibling tools (resolve, unclaim) that handle later lifecycle steps, so the tool is clearly distinguished from them without opening the schema.

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 states when to use the tool (for pending reviews) and how it fits in the workflow: pair with invariance_review_resolve when done or invariance_review_unclaim to release. It could be stronger by explicitly saying not to use it for already-claimed reviews or for read-only inspection, but the lifecycle guidance is clear and actionable.

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