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

With no annotations supplied, the description carries the full disclosure burden. It does well on response behavior: it explains each status value, the meaning of text, errorMsg, and doneUnits/totalUnits progress, and it adds a non-obvious retention constraint (terminal states kept 72 hours). It does not state read-only semantics, whether calling has side effects, or polling guidance, leaving gaps for an unannotated tool.

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 purpose is front-loaded and the status enumeration is compact and scannable, with no filler. The list-style formatting is efficient, though a single clause linking it back to submission would have cost nothing and added structure.

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 the definition need not restate return values, yet it helpfully maps status values to fields and documents the 72-hour retention window. What is missing is caller-side context – how task_no is obtained and how often to poll – which matters because there are no annotations to fall back on.

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 0% and the single required parameter task_no is undocumented in both the schema and the description. The definition spends all of its words on output semantics and never says where task_no comes from (presumably submit_transcription_task) or what format it takes, so it fails to compensate for the coverage gap.

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 definition names a specific verb and resource (query long-audio transcription task status) and scopes it to a single task. It does not explicitly distinguish itself from get_speech_task or get_document_task, so an agent must infer the difference from the word 'transcription', but the purpose itself is unambiguous.

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?

Usage is only implied: the status enumeration makes clear this is called to poll a task submitted earlier, but the description never says so, nor does it mention polling cadence or when to stop calling. No explicit when-not or alternative-tool routing is given.

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