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

With no annotations, the description carries full behavioral burden and does a solid job: it discloses terminal statuses, the timeout behavior, and that timeout returns the last-known state rather than an error. It omits minor details like error handling for unknown IDs or rate limits, but the core behavior is transparent.

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 sentences with no redundancy; the main action and terminal conditions are front-loaded, and the timeout nuance is delivered efficiently. Every clause adds value.

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?

The description covers terminal states and timeout behavior well, but there is no output schema and it never states what a successful poll returns. It also leaves the two timeout/poll parameters and their defaults unexplored, which is a meaningful gap for a blocking tool.

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 33%: id is documented but timeout_seconds and poll_interval_seconds are not. The description mentions 'timeout elapses' but never connects it to the timeout_seconds parameter or explains poll_interval_seconds, so it fails to compensate for the low schema coverage.

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?

Description states a specific verb ('poll') and resource ('a transcription'), and defines the exact stopping condition: terminal status or timeout. This clearly distinguishes it from get_transcription, which is a one-shot fetch rather than a blocking wait.

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 polling behavior and timeout semantics imply when to use the tool, and the timeout note explains how to handle non-terminal results. However, it never explicitly contrasts this with get_transcription or states when to prefer one over the other, leaving the routing partly to inference.

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