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

Annotations already cover the readOnly/idempotent/non-destructive safety profile, so the bar is lower, yet the description adds substantial context: pagination via nextOffset, that offset/limit count passages not words, ~30-second passage spans, and null timestamps for text-only transcripts. It also states scope boundaries ('does not transcribe again or summarize the speech'), which prevents miscalls.

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 core behavior, then pagination mechanics, then the alternative-tool routing. Every sentence carries a distinct piece of operational information with no redundancy or filler.

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 full burden of explaining returns, and it does so: passage structure with timestamps, nextOffset for continuation, and the null-timestamp case for text-only transcripts. Combined with usage routing, an agent has everything needed to call it correctly.

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 description coverage is only 25% (only projectId is documented in the schema), so the description must compensate, and it does for the important ones: offset/limit count passages rather than words, limit=40 as a starting value, and 'follow nextOffset when non-null.' assetId is left to context but is self-evident given transcribe_asset.

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 (read) and resource (a completed transcript), and explicitly distinguishes itself from the closest sibling by noting it returns 'continuous text in timestamped passages, not individual word rows.' An agent can tell it apart from read_analysis_range, transcribe_asset, and patch_transcript without opening any schema.

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 when-to-use ('Use this first to understand a conversation or find interesting clips') and when-not ('Use read_analysis_range with kind=transcript only when you need exact word timings for a chosen clip'). It even prescribes the starting invocation (assetId, offset=0, limit=40), leaving nothing to inference.

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