Server Quality Checklist

Tool Scores

• check_songA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It transparently states the outcome states: 'Returns the audio URLs if complete, an error if it failed, or 'processing' if still rendering.' It also discloses the non-blocking nature ('no waiting'). The description doesn't mention auth or side effects, but for a read-only status check this is adequate.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences with no filler. The main action and key differentiators ('single check with no waiting') are front-loaded, and every clause adds value by specifying behavior and return outcomes.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple tool with one parameter and no output schema, the description fully covers what happens: returns URLs on success, error on failure, 'processing' if pending. It also mentions the non-blocking behavior. The sibling names (generate_song, wait_for_song) provide additional context, making this description complete for the tool's complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the job_id parameter is fully described in the schema ('The job_id returned by generate_song'). The description only reiterates that the tool works 'by job_id' without adding additional syntax or format details. Baseline 3 applies as the schema already handles parameter semantics.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Get the current status of a song job by job_id'. It uses a specific verb ('Get'), specifies the resource ('song job'), and differentiates itself from siblings by emphasizing 'a single check with no waiting', which distinguishes it 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.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description conveys usage context by contrasting this tool with waiting: 'a single check with no waiting'. This implies it should be used for one-shot status checks rather than blocking until completion, effectively differentiating it from wait_for_song. However, it stops short of explicitly stating 'use this when you want to poll' or naming the alternative for waiting scenarios.

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

• generate_songA
  4.7/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries full burden. It discloses the async nature, expected duration (1-3 minutes), return type (job_id), and cost semantics ('Costs 10 tokens, billed only on success'). This is rich, non-obvious behavior.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three short sentences, each earning its place: what it does, what to do next, and cost implications. Front-loaded with the critical async return behavior. No fluff or redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description fully covers the async workflow, necessary follow-up (wait_for_song), and billing. Given the rich parameter schema and no output schema, the description sufficiently explains return values and next steps. Sibling context is also handled by the explicit reference to wait_for_song.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100% and each parameter already has a clear description (e.g., custom mode, prompt semantics, idempotency_key). The tool description itself adds no parameter-level detail, which is appropriate given the schema already does the heavy lifting. Baseline 3 is warranted.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Start generating a song with Suno.' It clarifies the async behavior ('Returns immediately with a job_id') and explicitly states what the tool does NOT do ('does NOT return audio'), distinguishing it 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.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicit usage guidance: 'After calling this, call wait_for_song with the returned job_id to get the audio URL when ready.' This clearly tells the agent the next step and prevents misuse by calling this tool expecting audio.

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

• wait_for_songA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and excels. It discloses polling limits (~45 seconds), return behavior on success vs. still rendering, idempotency (safe to call repeatedly), and that it never starts a new song. This is rich behavioral context.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences, front-loaded with the main purpose, then behavioral details, then safety. Every sentence earns its place with no redundancy or fluff.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite no output schema, the description fully explains the polling loop, success/retry paths, and safety profile. It is complete for a two-parameter tool with no annotations, covering both how and when to use it.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so baseline is 3. The description adds meaning by referencing 'same job_id' for retries and the ~45-second polling window, which complements the schema's max_wait_seconds parameter and clarifies intended usage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb+resource ('Wait for a song job to finish and return the audio') and clearly distinguishes itself from siblings: it polls for completion rather than just checking status (check_song) or creating a job (generate_song).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It gives clear context: use it after generating a song, and if not ready, call again with the same job_id. It implicitly differentiates from alternatives by stating it returns audio when ready, but does not explicitly mention check_song as an alternative for status-only checks.

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