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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description carries the real burden and does so well: exact cost ($0.05/episode, USD, never drawn from included requests), prerequisite (overage billing must be on), refund on failure, non-charged outcomes (existing/queued/already-held requests billed as ordinary lookups), expected latency (5–10 minutes), return states (queued/admitted/transcribed/failed with failure_reason), and post-transcription discoverability across sibling tools. This is unusually complete behavioral disclosure consistent with idempotentHint=true.

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?

Front-loaded with the eligibility rule, then billing, then lifecycle/polling — a sensible order for an agent. The prose is dense and slightly repetitive around billing outcomes, but nearly every clause supplies a fact an agent needs to avoid a wrong or duplicate (paid) call.

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?

There is no output schema, so the description must explain return values, and it does: the immediate response carries a request state with enumerated values and failure_reason on failure. Combined with cost, prerequisites, latency and handoff to polling/discovery tools, an agent has everything needed to call this correctly and follow up.

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% for the single episode_slug parameter, so the baseline is 3; the description adds value by explaining where a valid slug comes from (list_episodes with transcript_status=requestable and podcast_slug, or get_episode) and that the episode ID serves as the slug for back-catalogue episodes. It stops short of format/syntax examples.

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 and resource ('Request the transcription of a back-catalogue episode') and precisely scopes the eligible set: episodes found in a feed but not yet transcribed, marked requestable by particle_podcast_list_episodes (transcript_status=requestable) or particle_podcast_get_episode. It also clarifies what does not yet exist (transcript, segments, speakers, entities, mentions), so the agent can distinguish it from particle_podcast_get_transcription_request and the search/get tools.

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?

Explicit when-to-use (only requestable back-catalogue episodes), when-not-to-use ('never call this tool again to poll'), and the named alternative for polling (particle_podcast_get_transcription_request, described as free). It also imposes a procedural precondition rarely stated so plainly: confirm the $0.05 charge with the user first.

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