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

Annotations already declare this as readOnly and non-destructive. The description adds valuable behavioral context beyond that: it specifies the exact content of the response (full transcript plus source citation) and deliberately states that AI-generated summaries are excluded. This helps the agent set expectations about the response scope without contradicting the 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?

The description is just three sentences, front-loaded with the primary action ('Retrieve a single transcription'), then providing necessary detail about the return value and exclusions. Every sentence earns its place with no filler or redundancy.

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 simple read-only retrieval tool, the description covers the core behavior, the return payload, and an important exclusion. However, it omits any explanation of the 'lang' parameter and does not describe response format or error conditions. Given the annotations handle safety, the main gap is the undocumented parameter, making it mostly complete but not fully exhaustive.

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?

The input schema has 0% description coverage for its parameters, and the description does not explain them. While 'id' is inferable from the tool's purpose, the 'lang' parameter is completely undocumented—its meaning (e.g., language of the transcript or citation) is left ambiguous. The description fails to compensate for the schema's lack of parameter information.

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 clearly states the tool's purpose with a specific verb and resource: 'Retrieve a single transcription.' It goes further to specify that it returns the full transcript along with a source citation, and explicitly notes that AI-generated summaries are not returned, which distinguishes it from sibling tools like view_transcription or search_transcriptions.

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 description provides context that this is for retrieving a single transcription and mentions the endpoint it mirrors, but it does not explicitly state when to use this tool over alternatives such as view_transcription, nor does it give exclusions or prerequisites. The note about AI summaries implies an alternative but never names it, so usage guidance remains implied rather than explicit.

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