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

Annotations already cover read-only/idempotent safety, but the description goes well beyond them: it discloses the fallback when a plain-text transcript has no timing (returns text passages with a note) and what happens when no publisher transcript exists (reports episodes that do have one). These edge-case behaviors are exactly what an agent needs and are not in annotations.

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?

A single dense paragraph but front-loaded with the core capability, then defaults and edge cases in logical order. Nearly every sentence earns its place; the format list is slightly long but justified by the enum breadth.

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 compensates by describing the return shape — passages with start/end times, speakers when named, and matched words. Combined with documented fallback behaviors, an agent has everything needed to call and interpret results.

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 3 is the baseline; the description adds real value by explaining the default episode selection and the format-preference order (JSON, then WebVTT, then SRT, then text), which clarifies the 'format' enum's semantics beyond the raw schema. It doesn't clarify window_seconds, but that is well-documented in the schema.

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 opens with a concrete verb+resource+capability: fetching a publisher-provided transcript and returning passages matching a query with timestamps. It is sharply distinguishable from siblings like list_podcast_transcripts (which lists rather than searches). The parenthetical about Podcasting 2.0 formats adds precision without ambiguity.

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?

It clearly says when this applies (retrieving what was said about a topic) and how to select an episode (guid, URL, episode number, title words, or default newest-with-transcript). It stops short of explicitly contrasting with list_podcast_transcripts or get_podcast_profile, so an agent must infer the routing rather than being told.

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