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

The word 'Read' conveys a read-only operation, and the token estimates communicate response scale. With no annotations provided, the description carries the full burden, but it does not disclose output structure, error behavior, or what happens when no summary exists.

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?

The description is compact and front-loaded, with the purpose stated first and the parameter clarification placed immediately after. Every sentence earns its place without fluff or repetition.

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?

For a two-parameter read tool, the description covers the basics, but with no output schema and no annotations it leaves some context unstated, such as what exactly is returned, especially for the 'topics' detail level. It is adequate but not fully complete.

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?

The description adds meaningful value by explaining the `detail` parameter's allowed values ('brief', 'detailed', 'topics') and approximate token sizes, which the schema does not provide. The required `episode_id` is left to its self-explanatory name, but the most ambiguous parameter is well covered.

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?

The description clearly states the verb ('Read') and the resource ('an AI-generated summary of one episode'). It distinguishes itself from siblings like get_episode and search_episodes by focusing on the summary, though it does not explicitly name any sibling.

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?

The description implies usage: use this tool when you want an AI-generated summary of a single episode rather than the episode itself or search results. However, it gives no explicit when-to-use guidance, preconditions, or direct comparison with sibling tools.

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