Post Transcript

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

Goes well beyond the annotations: discloses the failure payload (null with transcriptNotAvailable), the billing rule (credits deducted only when a transcript is returned), the confirm=true requirement, and explains that the read-like POST does not publish to social platforms. That last point usefully reconciles the non-readOnly annotation with the actual side-effect profile.

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?

Two tight sentences: purpose and availability constraint first, then the return/billing/confirmation behavior. Every clause carries information; nothing is repeated from the schema or annotations.

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 correctly explains the null/transcriptNotAvailable case and the credit semantics, which an agent needs. It stops short of describing the success payload's shape or any rate limits, a minor gap for a credit-consuming call.

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 the baseline is 3, and the description adds real meaning for confirm (must be true for the specific approved credit-consuming call) and the credit consequences of the url call. The account parameter's semantics are left entirely to 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?

Specific verb+resource: fetching a video transcript from a LinkedIn post, with the scope qualifier 'when LinkedIn exposes one publicly'. It clearly separates itself from the generic linkedin_post sibling by naming the artifact (transcript) rather than the post, though it never explicitly names a sibling to route against.

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 concrete conditions: works only when LinkedIn exposes a public transcript, requires confirm=true, and consumes paid credits. It doesn't name an alternative tool for the no-transcript case or point to linkedin_post for non-video content, so the when-not branch is only partially covered.

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