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

Annotations already indicate a mutation (readOnlyHint false) and non-idempotent (idempotentHint false). The description adds valuable behavioral context: it flips status to 'generating', returns 202 immediately, and runs agents asynchronously before flipping back to 'review'. This explains the lifecycle and async nature, which the annotations alone do not cover. No contradictions with annotations.

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?

Three sentences, each carrying essential information: purpose, target types, and behavioral flow (status changes, async, immediate return). No redundancy or filler. Ideas are front-loaded: the first sentence is the most critical for intent. Perfectly efficient for the complexity involved.

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 covers purpose, target types, and key behavioral traits, but misses details about how to track the async process (e.g., response body, if any, or polling mechanism). It also glosses over the conditional id requirement ('identified by id in the body' is vague relative to the schema's conditional fields). Given the tool's moderate complexity (4 params, async, no output schema), these gaps lower completeness.

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 100% with all four parameters described. The description adds no new parameter-level details beyond the schema; it merely reiterates that the tool targets two snapshot kinds 'identified by id in the body'. This is consistent with the schema's conditional requirements but does not explain, for example, that type determines which id field is needed. Baseline 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 clearly states 'Re-run postprocessing agents on an existing v2 clarity snapshot' – a specific verb+resource combination. It distinguishes from related tools like generateClarityProcessSnapshot (which creates new snapshots) by emphasizing the 're-run' and 'existing' aspects. The two target snapshot types are explicitly listed, leaving no ambiguity about what the tool acts on.

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 provides context about when to use it (to re-run agents on existing snapshots of two specific types) but does not offer explicit when-not-to-use guidance or compare with sibling tools. For example, it doesn't mention that 'generateClarityProcessSnapshot' should be used to create a fresh snapshot instead. This leaves the agent without clear decision criteria against alternatives.

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