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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add what they can't: it explains that results are paginated by character offset and, importantly, that an in-progress recording returns status instead of text. That polling behavior is non-obvious and genuinely valuable; pagination token handling is left to the 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?

Three sentences, front-loaded with the core behavior, then usage, then format options. No filler and no 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 an output schema present and full schema description coverage, the description covers exactly the non-structured facts an agent needs: chunking, polling semantics, and available formats. Nothing required to invoke it correctly is missing.

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 baseline is 3, but the description adds rationale the schema lacks: why offset exists (transcripts can be very long) and how the format enum maps to user intent (plain text vs JSON segments vs subtitles). It stops short of explaining includeSpeakers/includeTimestamps interplay.

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 ('Returns the transcript of one recording by id') plus the defining constraint that output is chunked by character offset. It also distinguishes itself from the summarization/export siblings by describing what it returns (raw text, segments, subtitles) rather than a summary or an exported file.

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?

Gives explicit sequencing ('Call it after list_transcripts') and a second valid use case — polling a recording still processing. It does not explicitly say when to prefer get_transcript_summary or export_transcript, so the sibling routing is incomplete but the primary context is clear.

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