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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real value beyond that: the default returned sections and the precondition that the episode must first be transcribed, with a fallback action (process_episode).

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 sentences, front-loaded with the core action, then default output, then the sections option and the precondition. 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?

With no output schema, the description carries the return-value burden and does so by enumerating the default sections (overview, takeaways, chapters, highlights) and the optional ones (qa, keywords, mindmap), plus the transcription prerequisite. Complete for an agent to call correctly.

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%, so each parameter is already documented, including section defaults and the seq format. The description largely restates the default-sections behavior without adding format or enumeration detail beyond the schema, so 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 and resource: 'Get the AI-generated summary of a transcribed episode.' This clearly distinguishes it from siblings like get_episode (metadata) and get_episode_transcript (raw transcript).

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?

Explains default behavior and how to narrow or extend output via sections, and routes to process_episode when the episode is not yet transcribed. It gives clear context but does not explicitly contrast with other retrieval siblings such as get_episode or get_episode_transcript.

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