tunova

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

No annotations provided, but description fully discloses behavior: returns three states (complete URLs, error, processing) and non-blocking nature ('no waiting'). No contradictions.

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?

Single sentence that is front-loaded with purpose, efficient, and contains no extraneous information. Every word is necessary.

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?

Given no output schema, description completely covers return types (audio URLs, error, processing) and input origin. No gaps for a simple poll 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 has 100% description coverage for job_id. Description adds context that job_id comes from generate_song, reinforcing the tool's dependency and usage pattern.

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?

Clearly states verb 'Get the current status' and resource 'song job by job_id'. Distinguishes from siblings by noting 'single check with no waiting', contrasting with wait_for_song.

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?

Implies usage for one-time checks without polling via 'no waiting', but does not explicitly state when to use vs alternatives or provide exclusions. Sibling tools are named but no direct comparison.

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

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

Despite no annotations, the description fully discloses behavioral traits: asynchronous execution (returns immediately, render takes 1-3 minutes), cost (10 tokens billed only on success), and that it does not return audio. This is comprehensive and leaves no hidden behaviors.

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 three sentences long, front-loaded with the core purpose, and contains no superfluous information. Every sentence earns its place, making it efficient and easy to parse.

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?

Given the tool's complexity (async, 6 params, siblings, no output schema), the description is complete: it covers async behavior, cost, sequencing instructions, and mode differences. The absence of output schema is fine because the description clarifies the return value (job_id) and that audio is not returned.

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 for parameter semantics is 3. The description adds significant value beyond schema by explaining the distinction between custom mode (prompt as lyrics) and simple mode (describe the song), and how tags/title are used. This enhances understanding beyond the param descriptions.

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 clearly states the tool starts generating a song with Suno and distinguishes it from siblings by explaining it returns a job_id, not audio. This directly tells the agent what the tool does and how it differs from wait_for_song.

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 explicitly tells when to use the tool (to start generation), what not to expect (no audio), and the next step (call wait_for_song with the job_id). It also mentions cost and success billing, providing complete usage guidance with no ambiguity.

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

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

No annotations provided, so description carries full burden. It discloses polling, max wait time, return behavior (clips with URLs or status), and safety (read-only, no new song creation). This is sufficient for transparency.

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 sentences, each adding distinct information: purpose, polling time, outcomes, safety. No unnecessary words, well front-loaded.

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?

Given no output schema, description explains returns (clips with audio URLs or status). Could be more precise about status structure, but adequate for a polling tool with 2 parameters.

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%, baseline 3. Description adds context beyond schema: explains job_id is from generate_song and max_wait_seconds default/max. Also clarifies polling behavior and that it returns status for retries, adding meaning.

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 clearly states the verb 'wait for' and the resource 'song job'. It distinguishes itself from sibling tools by emphasizing it only reads status and never starts a new song, contrasting with generate_song.

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 explains that it should be used after generate_song, can be called repeatedly if not ready, and is safe. It implicitly suggests using this for polling but does not explicitly mention when to use check_song instead.

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