List transcripts needing Codex proposals

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

Description aligns with annotations (readOnlyHint=true) by stating returns a batch; adds context about boundedness and expected follow-up actions.

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 concise sentences, front-loaded with purpose, no wasted words.

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?

Sufficient for a simple list tool with pagination; instructions on next steps compensate for lack of output schema.

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?

No parameter descriptions in schema or description; limit and cursor are self-explanatory from schema constraints, but description adds no value.

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?

Description clearly states the tool returns a batch of raw transcripts needing proposals, with explicit instruction to generate corrections and call save_correction_proposals, distinguishing from 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?

Explicitly states the action to take with results and references sibling tool save_correction_proposals, but lacks when-not-to-use guidance.

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