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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds valuable context those annotations don't carry: credit consumption requiring user confirmation, asynchronous execution, and the polling contract. It does not disclose what destructive behavior means here (e.g. whether existing transcript/summary is overwritten), which is the one notable gap.

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, no filler, and the cost warning and async contract are front-loaded where an agent will read them before invoking.

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 no output schema, the description still closes the loop an agent needs: it says processing is asynchronous and names get_episode as the completion check. For a one-parameter, one-effect tool with full schema coverage, nothing essential is missing.

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% and the single 'seq' parameter is fully documented in the schema with an example URL and exclusivity constraint. The description adds no parameter-level meaning, so the baseline 3 applies.

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?

States a specific verb+resource ('Start AI processing ... for an episode') and enumerates the concrete outputs produced (transcription, summary, outline). It is immediately distinguishable from read-only siblings like get_episode_transcript or get_episode_summary.

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?

Gives a real precondition ('may consume the user's AI processing credits, so confirm with the user first') and routes the agent to the follow-up call ('poll get_episode until it is done'). It stops short of stating when not to use it, e.g. if an episode is already processed.

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