Yedapo podcast summaries

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world behavior. The description adds valuable context beyond that: it enumerates the summary's returned sections and states the output is markdown with a citable page URL, which matters since there is no output schema.

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?

One front-loaded sentence that names the resource, the output format, and the returned sections with zero filler. Every clause carries information the agent can use.

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 single-param, read-only fetch, the description plus full schema coverage plus annotations cover everything needed. It compensates for the missing output schema by describing the summary structure and the citation URL.

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% and already documents that the parameter accepts a UUID or a yedapo.com episode URL with UUID extraction. The description adds no parameter-specific guidance beyond what the schema provides, 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?

Specific verb and resource ('Get one episode's full Yedapo summary') plus the exact deliverable format (markdown, teaser, verdict, takeaways with timestamps, chapters, page URL). The 'one episode' scope naturally separates it from the sibling search_episodes listing tool.

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?

Usage is only implied – it fetches a single episode's summary, so an agent can infer it should call this when it already has an episode identifier. There is no explicit when/when-not guidance or reference to search_episodes for discovery.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds real behavioral context beyond them: the exact match surface (title, show name, topic tags, teaser), the 10-result ceiling, the 'newest first within each match type' ordering, and the per-result payload including a citable page URL.

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 sentences, each dense with non-redundant information, and the search scope is front-loaded before the match surface and return shape. No filler or restatement of the title.

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 fully: match cap, ordering, and the fields of each result including the citation URL. An agent can invoke it and act on the output without opening anything else.

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 only 50% (the limit property has no description), and the description compensates by explaining that results are capped at 10 and by enumerating exactly which fields the query matches against. It does not clarify that limit is caller-adjustable from 1 to 10, so the cap reads as fixed rather than tunable.

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 ('Search Yedapo's ~3,500 AI summaries of podcast and YouTube episodes') and immediately scopes what is searched. It also distinguishes itself from the sibling by noting each result carries 'the episode id for get_episode', so the agent knows this is discovery, not retrieval.

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 parenthetical '(not full transcripts)' is an explicit exclusion that tells the agent this tool cannot answer content-level questions, and the get_episode handoff implies the follow-up path. There is no explicit 'when not to use' statement or named alternative for non-episode content, which keeps it from a 5.

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