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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description must add value beyond that. It does: polling cadence, latency expectations, and the important billing note that 'reading a transcript does not use the allowance.' It briefly notes the ready-state result contains the text, though it does not describe failure/error states.

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?

Four short sentences, front-loaded with the trigger condition before the polling guidance, and every sentence carries actionable information (trigger, cadence, duration, billing). No 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?

An output schema exists, so return-value documentation is unnecessary. The description covers the lifecycle of the poll (when to call, how often, when done) plus the quota behavior, giving the agent 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 100%, so the schema already documents transcriptId and maxChars fully. The description references the transcriptId's origin ('returned by get_transcript' via the sibling) but adds no syntax or semantics beyond the schema. Baseline 3 is appropriate.

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 ('check on a transcript') and explicitly ties it to the sibling get_transcript by describing the situation it operates on ('a transcript that get_transcript returned as processing'). An agent can distinguish it from get_transcript without opening either 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?

Explicitly states when to use it (after get_transcript reports processing), the polling cadence ('call again every 20 seconds or so'), and the expected duration ('long audio can take several minutes'), which also implies when to stop polling. Nothing is left to inference.

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