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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: per-account read scoping, an API key requirement, and per-call billing routed to list_services. For a paid authenticated fetch these are exactly the operational facts an agent needs.

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?

Three tight clauses, front-loaded with what the tool returns, then the keying, then the access and cost constraints. No filler and nothing buried.

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?

Covers return shape, auth, billing, and access limits for a read-only tool with no output schema. The one gap is transcript length handling (truncation or size limits on long episodes), which matters for a bulk text payload.

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 0%, so the description must carry the burden, and it does: it maps the two params to podcast id (sid) and episode id (pid) and tells the agent where those values come from. It doesn't restate UUID format, but the schema's format field handles that.

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 (fetch one episode's transcript) with its return shape (speaker turns and timestamps) and its keying (podcast and episode id). The singular, one-episode scope cleanly distinguishes it from the plural sibling search_transcripts.

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?

Clarifies the provenance of the required identifiers ('the sid and pid of a search result'), implicitly routing the agent to search first and then fetch. It stops short of naming search_transcripts or ask_question as explicit alternatives or stating when not to use this tool.

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