Read a transcript

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses the failure mode and its error identifier (not_ready), warns that long recordings return a lot of text, explains that from/to pull whole overlapping paragraphs, and notes that format/from/to are ignored when summaryOnly is set. This is operational context an agent cannot derive from annotations or 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?

Front-loaded with the resource and format contract, then progressively narrower guidance (windowing, summaryOnly, error state) — no sentence is filler. Some clauses are dense, e.g. the parenthetical "(what the app shows)" vs "the app's Export menu makes", but each carries real meaning for format choice.

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 seven parameters, no output schema and a read-only annotation set, the description covers what is returned per format, how to bound large payloads, the summary substitution, and the not-ready case. It does not spell out the exact json segment structure beyond 'word timings and speakers', a minor gap given there is no output schema.

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 already 86%, so the baseline is 3; the description earns above that by explaining intent for from/to (paragraphs overlapping a moment, e.g. a search_transcriptions match), what summaryOnly swaps in (the get_summary payload), and the format split between app-style json and export-file text.

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 by naming the resource returned ("The finished transcript") and immediately differentiates the four output formats: json yields segments with word timings and speakers, while txt/srt/vtt yield exported file text. That distinguishes it from a status tool like get_transcription and from get_summary without needing the schema, though the opening is a noun phrase rather than an explicit 'read the transcript of...' verb.

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 gives explicit conditional guidance: pass from/to for paragraphs around a moment (naming search_transcriptions as the source of such a moment), use summaryOnly for the summary, and 'check get_transcription first' when the transcript is not ready. Both the alternative tool and the exclusion condition are stated.

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