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

Annotations already convey non-read-only, non-idempotent, non-destructive behavior. The description adds the useful async behavior: it waits up to 240 seconds and, if incomplete, returns job_id and the next query step. This goes beyond annotation data and gives an agent a realistic model of the call's outcome.

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 a single dense sentence: it front-loads the main action and then gives the key async behavior. No filler or redundant phrasing.

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 one-parameter submission tool with a detailed schema and an output schema, the description covers initiation, wait behavior, and incomplete-job handling. It also tells the agent what to do next if the job is not finished, so nothing critical is missing.

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%%, and the schema property description already fully documents accepted URL formats and exclusions. The tool-level description adds no additional parameter semantics beyond what the schema already provides, so the baseline of 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?

The description names a specific action (submit speech-to-text transcription) and a specific resource (Zhihu standalone video page or video answer page link). It clearly differentiates from the sibling zhihu_submit_video_speech_text_by_zvideo_id by targeting URL-based input rather than zvideo ID.

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 states when to use this tool: with a standalone video URL or a video-bearing answer URL. It explicitly lists unsupported inputs (plain answers, articles, question pages, profiles, interfaces, short links, and numeric-only IDs), giving clear exclusions. It does not explicitly name the sibling alternative for zvideo_id-only inputs, but the accepted formats imply the distinction.

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