postfader_review_start

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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which already convey much of the safety profile. The description adds the bounded nature of the session and the requirement of a completed run, complementing the annotations. However, it doesn't explicitly clarify that this could still initiate analysis or planning work (despite readOnlyHint), nor does it discuss session persistence behavior; the schema covers defaults like persist_session but real-world effects like side effects on the run are not described.

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 a single, efficient sentence that front-loads the core purpose and a key constraint. It avoids fluff and is appropriately sized for the complex schema provided separately.

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 tool with a very detailed schema and annotations, the description is functional but leaves a gap: it doesn't mention the interaction_policy, evaluation_policy, or user_feedback that the schema supports, nor does it clarify that this is the 'start' counterpart to postfader_review_stop. The output schema is not shown here, but the schema's richness compensates for much of the description's brevity. Still, the agent would benefit from knowing this tool is also the one that accepts user feedback for a bounded review.

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?

Parameter coverage is 100% and the schema contains rich descriptions on nested objects (e.g., ReviewSessionRequest, CreationFeedback, ReviewPreserveRules). The description of the 'request' property matches the top-level description, so the text adds little new semantic meaning beyond the schema. The baseline 3 applies here.

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 'Start a bounded Review Session from one completed Production Run.' uses a specific verb ('Start'), a distinct resource ('bounded Review Session'), and a clear precondition ('completed Production Run'). It distinguishes this tool from siblings like postfader_continue_run and postfader_review_get by emphasizing session creation from a run, though it doesn't explicitly name those siblings.

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 and the ReviewSessionRequest schema strongly imply this is the entry point for review sessions, especially given the required source_run_id and the annotation title 'Start a Creation Review.' While it doesn't explicitly state when not to use it or name alternatives, the context of sibling tools like postfader_continue_run and postfader_review_get makes the usage context reasonably clear.

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