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

The description clarifies the async nature ('Returns 202 immediately and finalises asynchronously via the cc-server webhook stream'), which annotations lack. It also indicates which fields are relevant per kind. However, it does not detail what happens on failure, rate limits, or whether the operation is cancellable. Given annotations only show non-destructive and non-idempotent hints, the description adds meaningful behavioral context.

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?

The description is relatively concise at two sentences, front-loading the main action and then detailing kind-specific behavior. Minor redundancy (e.g., 'generate or regenerate proposal pipeline' could be tightened) but overall efficient for the complexity.

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 6 parameters, 100% schema coverage, no output schema, and moderate complexity (two pipeline kinds, async behavior), the description covers the key behavioral aspects and parameter applicability. Slight gap: it doesn't explain the role of 'source_snapshot_id' default or how to poll for completion. Still, for a tool with rich schema descriptions, this is mostly 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?

Schema description coverage is 100% with rich descriptions for each parameter (e.g., 'custom_guidance' is 'high-priority design guidance, not source-of-truth evidence'; 'regenerate_from' specifies it runs the regenerate pipeline using that proposal's current-process snapshot). The description further adds context about which parameters apply to which kind, and the async return behavior, which goes beyond the 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?

The description clearly specifies the verb ('trigger a snapshot generation pipeline') and the resource ('v2 clarity process'), plus distinguishes between two specific kinds ('current_process' and 'transformation_proposal') with concrete behaviors. This differentiates it well from sibling tools like 'getClarityProcessSnapshot' (read) and 'saveClarityProcessSnapshot' (save).

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 explains when to use each 'kind' value, including specific body field conditions for 'current_process' and the distinction between generate vs. regenerate for 'transformation_proposal'. It implicitly indicates this is for initiating snapshots as opposed to reading or saving, but does not explicitly exclude alternative tools or state when NOT to use it.

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