Server Quality Checklist

Tool Scores

• flow_waitA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral burden. It discloses the polling mechanism (every 5 seconds) and the timeout limit, which is useful, but it does not specify what happens when timeoutSec is exceeded, whether polling stops immediately, or how failures are reported.

  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 a single compact sentence that front-loads the main purpose and then adds the key behavioral detail. There is no filler, repetition, or unnecessary context.

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

  Completeness4/5

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

  For a simple two-parameter wait operation with no annotations and no output schema, this description covers the main behavior, the return value, polling cadence, and timeout. The only notable gap is the timeout-exceeded behavior and how to obtain a valid jobId, which prevents a perfect score.

  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 only 50%, so the description should help compensate. It slightly enriches timeoutSec by stating that polling occurs up to that limit, but jobId is only implied by the word 'job' and gains no additional semantic detail beyond its property name.

  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 states a precise action (wait), the target (a job), and the outcome (returned file paths). This clearly differentiates it from sibling tools like flow_status, which checks status without blocking, and flow_generate/edit/cancel, which do not wait and return paths.

  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 makes clear that this tool is the blocking wait-and-collect step after a job has been started, with a timeout limit. It does not explicitly name alternatives or state when not to use it, so it falls just short of a top score.

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

• flow_cancelA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the disclosure burden. It clearly discloses the key behavioral trait: pending items are removed, but already-started clips continue. It does not mention reversibility or response behavior, but the core side effect is transparent.

  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 short sentences with no filler. The main action is front-loaded, and the boundary condition is stated immediately after.

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

  Completeness4/5

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

  For a zero-parameter cancellation tool with no output schema, the description is sufficiently complete to invoke correctly. It explains what will be removed and what will be preserved, leaving little ambiguity for the agent.

  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?

  The input schema has zero parameters and complete schema coverage, so there is nothing for the description to add about parameter meaning. With 0 params, this is a solid baseline.

  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 states a specific verb ('Remove') and a clear resource/scope ('everything that has not started generating yet'), and explicitly distinguishes what is affected from what is not. This makes its purpose distinct from siblings like flow_generate, flow_status, and flow_edit.

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

  Usage Guidelines3/5

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

  The description implies when to use the tool: when you want to cancel generation tasks that have not started. However, it does not explicitly name alternatives or state when not to use it beyond noting that in-progress clips are not interrupted.

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

• flow_editA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral disclosure burden. It does well by revealing the workflow: the extension opens the last clip, applies the change, and downloads the result. It also discloses the trusted-input requirement and the asynchronous nature via flow_wait. It does not explicitly state whether the original file is modified, which is a minor gap for an edit operation.

  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. It front-loads the core purpose — editing an already finished video — then packs the necessary behavioral details and prerequisites into the remainder. Every clause adds useful information.

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

  Completeness4/5

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

  Given no output schema and no annotations, the description covers the essential operational facts: what the tool does, what prerequisite must be met, and how to wait for the async result. It is slightly light on what happens to the original clip and on explicit disambiguation from flow_generate, but an agent can still select and invoke this tool correctly.

  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%, so the schema already documents both parameters. The description adds little beyond the schema: 'applies the described change' loosely maps to the prompt parameter, and the English-language tip already appears in the schema. This is the baseline case where the schema does the heavy lifting.

  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 states a specific verb and resource: 'Edit an ALREADY FINISHED video in the Omni 1.1 editor (video-to-video)'. It also clarifies the mechanism — opens the last clip in Flow, applies the change, downloads the result — which distinguishes it clearly from sibling tools like flow_generate that create new content rather than edit existing clips.

  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 gives clear context: use this when editing an already finished video, not for generation. It also provides concrete operational guidance with the prerequisite 'Requires "Trusted input" enabled in the extension' and the follow-up instruction 'Wait for the result with flow_wait'. It does not explicitly name flow_generate as the alternative for new videos, but the context is strong.

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

• flow_generateA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full behavioral burden. It discloses asynchronous queuing (returns immediately), the reliance on the bridge to read absolute file paths, and the cross-machine limitation. Minor failure modes or side effects are not discussed, but core behavior is transparent.

  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?

  Two sentences with no filler. The first sentence establishes purpose and immediacy; the second adds the path caveat and remediation. Each sentence earns its place and is front-loaded.

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

  Completeness4/5

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

  Given the tool's complexity, the lack of annotations, and the absence of an output schema, the description covers the critical non-obvious behavior: async jobId return, file path assumptions, and the bridge machine constraint. Remaining parameter details are fully documented in the schema, so nothing essential is missing.

  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 description coverage is 100%, which sets the baseline at 3. The description adds meaningful semantics for frames and characters: their paths are absolute, read by the bridge, and unusable from another machine. This goes beyond the schema's per-field descriptions.

  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 states a specific verb and resource: 'Queue a generation in the live Google Flow through the extension.' It also explicitly contrasts itself with flow_wait by noting it returns jobId immediately and does not wait for clips, making sibling differentiation clear.

  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 gives an explicit alternative ('wait with flow_wait') and a concrete when-not-to-use condition: file paths on another machine are unreachable, so the user must copy files to the bridge machine. It does not enumerate all sibling tools, but it covers the most important routing decision.

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

• flow_statusA
  4.6/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses what state is inspected and reveals important behavior such as queue auto-resuming after license activation. It stops short of stating whether the call is side-effect-free or describing the exact response format, so it is not a 5.

  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 compact and front-loaded: it opens with the returned state categories, then immediately gives actionable sequencing and license guidance. Every sentence contributes useful information with no repetition or padding.

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

  Completeness4/5

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

  With no output schema and no annotations, the description does well to enumerate the key state fields and preconditions. It could be more explicit about possible values or response shape, but the tool is simple and the guidance is sufficient for an agent to call it correctly.

  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?

  The input schema has zero parameters, so there is nothing for the description to clarify. Per the baseline for parameterless tools, this is fully adequate.

  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 states exactly what the tool reports: connection state, open Flow tab, queued items, and the director playbook. This is clearly a status/read tool and is easily distinguished from sibling action tools like flow_generate, flow_edit, flow_wait, and flow_cancel.

  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?

  It gives an explicit directive to call the tool BEFORE generating, with a concrete consequence: without a live Flow tab, tasks pile up. It also provides conditional handling for an expired license, including the next user action and expected queue behavior after activation.

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