Server Quality Checklist

Tool Scores

• seeany_generate_product_imageB
  3.3/5.0
  Behavior4/5

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

  Beyond the annotations (which only indicate read/write hints), the description discloses the asynchronous nature of the task and directs the agent to a wait step. This is useful behavioral context that helps the agent understand the tool's execution model.

  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?

  A single, front-loaded sentence that conveys the core action and the required follow-up with zero filler. Every word earns its place.

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

  Completeness2/5

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

  For a 7-parameter async task with no output schema, the description is too thin. It doesn't explain what the immediate response contains (e.g., a task ID), how the wait step connects, or what the parameters mean. The workflow hint is helpful but insufficient for correct invocation.

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

  Parameters1/5

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

  Schema description coverage is only 14%, so the description must compensate for undocumented parameters, but it doesn't mention any parameter semantics at all. The agent is left with raw enum values and defaults but no explanation of what count, model, or resolution actually affect.

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

  Purpose4/5

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

  The description clearly states the tool creates an asynchronous SeeAny product-image task, with a specific verb and resource. It also points to seeany_wait_generation as the follow-up, which distinguishes it from the retrieval/wait siblings, though it doesn't explicitly differentiate it from seeany_create_product_visual.

  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 gives a clear workflow context: create the async task, then wait for results. However, it provides no guidance on when to choose this tool over seeany_create_product_visual or other generation siblings, and no exclusions or alternative routing.

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

• seeany_refine_promptB
  3.4/5.0
  Behavior3/5

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

  Annotations indicate non-read-only, open-world, non-destructive behavior, and the description does not contradict them. It adds the core behavior of transforming a rough prompt into a refined one, but it does not explain how action, extra_context, or reference_asset_ids influence the result, nor what the returned output looks like.

  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 front-loaded sentence with no filler. It efficiently communicates the tool's purpose and transformation without wasting words.

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

  Completeness2/5

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

  Given four parameters, no output schema, and sibling tools for image generation, the description is too thin. It does not explain the parameters, when to prefer this over generation tools, or what the refined prompt output contains, leaving important gaps for an AI agent.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate for the four undocumented parameters. It only indirectly clarifies the 'prompt' parameter and leaves 'action', 'extra_context', and 'reference_asset_ids' unexplained, including the meaning of the enum values.

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

  Purpose4/5

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

  The description states a clear verb ('refine') and resource ('SeeAny AI prompt refinement'), and explains the transformation from a rough product-image request to a production-ready prompt. It does not explicitly distinguish itself from siblings like seeany_generate_product_image, but the purpose is still 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 clearly implies when to use the tool: when the user has a rough product-image request and needs a refined, production-ready prompt. It does not mention alternatives or exclusions, but the context is sufficient for an agent to select it over image-generation or asset-management tools.

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

• seeany_wait_generationA
  3.5/5.0
  Behavior3/5

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

  Annotations already declare the operation read-only and non-destructive. The description adds useful behavioral context by indicating that the tool blocks until a terminal state or timeout. It does not, however, explain what constitutes a terminal state, whether it returns partial status updates, or what happens on timeout beyond the parameter constraints.

  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, clear, front-loaded sentence. It wastes no words and conveys the core action, target resource, and termination condition efficiently.

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

  Completeness3/5

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

  For a simple polling tool, the essentials are present, but there is no output schema and the description does not mention what the response contains or what terminal state values might look like. This is a noticeable gap, though the tool is simple enough that an agent could still invoke it correctly with the given schema and annotations.

  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 0%, so the description carries the burden of explaining parameters. It indirectly clarifies timeout_seconds by referencing the timeout expiring, and job_id is implied to identify the generation task. The parameter names are fairly self-explanatory, but the description does not explicitly define job_id's origin or the exact effect of timeout_seconds beyond the schema constraints.

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

  Purpose4/5

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

  The description clearly states the verb 'Poll', the resource 'SeeAny generation task', and the exit condition 'until it reaches a terminal state or the timeout expires.' This sufficiently conveys the tool's purpose and implicitly distinguishes it from a one-shot status check like seeany_get_generation, though it does not explicitly name the sibling alternative.

  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 wait for a generation task to finish rather than just fetch its current state. However, it does not explicitly state when not to use it or point to seeany_get_generation for single status checks, leaving the choice partly to inference.

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

• seeany_get_generationA
  3.7/5.0
  Behavior4/5

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

  Annotations already mark the call read-only; the description additionally reveals what the response contains (status, progress, output URLs) and the 'latest' nature, which is useful for repeated polling. It does not describe error cases or the lifecycle of output URL availability, but with read-only annotations the burden is lower.

  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?

  One sentence, front-loaded with the action and object, listing the three return groups with no filler. Every word contributes to the agent's understanding.

  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 one-parameter, read-only getter with no output schema, the description covers the essential return areas and implies polling. It could mention that output URLs appear only after completion and point to wait_generation, but those are secondary for simple invocation.

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

  Parameters2/5

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

  With schema description coverage at 0%, the description needed to explain that job_id comes from a generation-creation call and how to obtain it. It does not; it only implies the task context. The property name is self-evident, but no sourcing/format guidance is provided.

  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 identifies a specific verb ('Get'), a specific resource (a SeeAny generation task), and the exact data returned (status, progress, output URLs). 'Latest' signals a polling/query behavior, distinguishing it from sibling seeany_wait_generation, which implies blocking.

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

  Usage Guidelines2/5

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

  No guidance is given about when to call this tool versus seeany_wait_generation or seeany_download_assets. The description only implies it is for checking a task; it does not state exclusions or polling semantics.

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

• seeany_download_assetsA
  3.9/5.0
  Behavior4/5

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

  Annotations only mark the tool as non-read-only and non-destructive. The description adds real behavioral context: it writes output files into a local directory and returns their paths. It does not mention overwrite behavior or directory creation, but for a download operation the core side effect is disclosed.

  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?

  A single sentence with no fluff: action, resource, destination, and return value are all front-loaded. Every word contributes to understanding.

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

  Completeness3/5

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

  For a simple two-parameter download tool, the description covers the main flow but leaves gaps like output_dir creation/overwrite behavior and the exact representation of returned file paths. It is adequate but not fully self-sufficient.

  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 0%, so the description must carry the burden. It indirectly maps output_dir to 'local directory' and job_id to a 'completed SeeAny' job, adding some meaning, but it does not explain formats, whether output_dir is auto-created, or required job state in detail.

  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?

  States a specific action (download), resource (completed SeeAny output images), destination (local directory), and return value (file paths). It is clearly distinct from siblings like upload_asset or get_generation, none of which download output images.

  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 word 'completed' implies this should be used after a SeeAny generation has finished, which is a useful contextual cue next to wait_generation. However, it never explicitly says when to use this versus alternatives, and no exclusions are mentioned.

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

• seeany_get_capabilitiesA
  4/5.0
  Behavior4/5

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

  Annotations already declare this read-only and non-destructive, so the description only needs to add meaningful behavioral context. It does so by specifying exactly what information is returned: models, ratios, resolutions, and execution mode. This goes beyond a vague 'get capabilities' without contradicting the annotations.

  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 action and directly lists the returned data categories. Every word contributes meaning, with no filler or redundant restatement of the tool name.

  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 read-only capability-listing tool, the description is sufficiently complete: it names the output categories and there is no output schema to elaborate. Minor gap is the lack of any indication of how the returned values are structured or formatted, but this is low-impact for this tool type.

  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 tool has zero parameters and schema description coverage is 100%, so there is no parameter documentation burden on the description. With no parameters, the baseline of 4 applies and the description needs no further parameter-level detail.

  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?

  Description clearly states a specific verb ('List') and a precise resource scope (SeeAny image generation models, ratios, resolutions, and current execution mode). This distinguishes it from siblings like get_account or generation-oriented tools without appearing generic.

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

  Usage Guidelines2/5

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

  There is no explicit guidance on when to call this tool versus the sibling tools. While its purpose is fairly obvious, the description does not mention that it should be used for discovery before generation, nor does it state any conditions or alternatives.

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

• seeany_plan_product_visualA
  4/5.0
  Behavior4/5

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

  Annotations already mark the operation read-only and non-destructive; the description adds that no paid generation task is created and that the result is a plan_id for later execution. This is useful behavioral context beyond the annotations, though it doesn't detail plan validity or side effects.

  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 entire description is one efficient sentence with the action and key distinction front-loaded. Every clause carries useful information, with no filler.

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

  Completeness3/5

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

  For an 8-parameter planning endpoint without an output schema, the description gives a minimal but viable picture: plan, estimate cost, get plan_id. It omits how plan_id should be used to execute the job and what plan details/cost breakdowns the agent should expect.

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

  Parameters2/5

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

  Schema coverage is only 38%, and the description adds no parameter-level explanations. Most of the eight parameters (count, model, use_case, resolution, aspect_ratio) must be understood from their names/enums; the description does not compensate for the low coverage.

  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 action ('Plan... product-visual job'), clarifies the non-paid nature, and names the return value (plan_id). This distinguishes it from paid execution siblings like seeany_create_product_visual.

  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 clearly positions the tool as the estimation/planning step before 'explicit execution,' and the phrase 'without creating a paid generation task' signals when not to use this. It does not explicitly name the sibling to use for execution, but the workflow context is clear.

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

• seeany_quote_generationA
  4/5.0
  Behavior4/5

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

  Annotations already mark it read-only and non-destructive, so the description does not need to prove safety. It adds a valuable behavioral caveat: this is only an estimate and does not reserve credits, which prevents an agent from assuming side effects. It does not detail response behavior, but the key non-mutating trait is covered.

  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 very short sentences with no filler. The first states the core purpose immediately; the second earns its place by addressing the credit-reservation misconception.

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

  Completeness3/5

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

  Given that there is no output schema, the description should explain what kind of quote/cost result will be returned, but it does not. It also leaves parameter semantics to inference. Still, the tool is simple and the selection context is present, so this is minimally viable rather than severely incomplete.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description does not explain the meaning of model, count, use_case, or resolution. The agent must rely entirely on names and enum values. The description also does not connect these parameters to how cost is calculated.

  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?

  Description clearly identifies the tool as a cost estimator and frames it as a pre-task step, which distinguishes it from siblings like create_product_visual or generate_product_image. The verb 'estimate' and resource 'generation cost' are specific and non-tautological.

  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 phrase 'before creating a task' gives an explicit when-to-use signal. It does not name alternative tools or state when not to use it, but the temporal context is clear enough for an agent to route appropriately.

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

• seeany_get_accountA
  4.3/5.0
  Behavior4/5

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

  The description adds meaningful behavioral context beyond the annotations: it discloses that the tool reports an environment/mode status (local demo vs authenticated API). The annotations already mark it as readOnly and non-destructive, and the description is consistent with those safety signals.

  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, front-loaded sentence with no filler. Every word contributes to explaining the tool's purpose, making it easy for an agent to parse quickly.

  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 zeroparameter, read-only status-check tool, the description is complete. It explains what the tool reports ('whether this MCP is using the local demo or the authenticated SeeAny API') and the annotations cover sideeffect and safety characteristics. No output schema is needed for such a simple status query.

  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 the description correctly implies no inputs are needed. Since there are no parameters to document, the baseline of 4 applies; the description adds no misleading parameter information.

  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 ('Show') and names the exact resource being checked: whether the MCP is using the local demo or the authenticated SeeAny API. This clearly distinguishes it from siblings like seeany_get_capabilities and seeany_generate_product_image, which serve different purposes.

  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 intended use is implied by the description: call this when you need to know whether the MCP is running against the local demo or the authenticated API. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention any excluded scenarios.

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

• seeany_upload_assetA
  4.3/5.0
  Behavior4/5

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

  Annotations already indicate this is not read-only, and the description confirms the mutating upload behavior while adding the useful detail that it returns an asset id and URL. It does not disclose potential constraints like supported file types or size limits, but for a simple upload tool this is reasonably 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?

  One sentence, front-loaded with the core action and outcome, with no filler or redundant detail. Every word earns its place.

  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 single-parameter upload tool with no output schema, the description adequately covers the action, the input path concept, and the return values (asset id and URL). The relationship to later generation is also mentioned, making the tool self-contained enough for correct invocation.

  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% and the single parameter file_path is already described as 'Absolute or workspace-relative local image path.' The description adds only the word 'local' and 'product image,' which largely restates schema information rather than adding new parameter meaning. Baseline 3 applies.

  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 ('Upload'), a resource ('local product image'), and a concrete outcome ('return an asset id and URL for later generation'). This clearly differentiates it from sibling tools like seeany_download_assets and seeany_generate_product_image.

  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 phrase 'for later generation' gives clear contextual guidance on when to use this tool, positioning it as a prerequisite step before image generation. It does not explicitly name alternatives or exclusion conditions, but the purpose is clear enough for an agent to select it correctly.

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

• seeany_create_product_visualA
  4.4/5.0
  Behavior5/5

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

  The description adds meaningful behavior beyond the annotations: it waits for a stored job, downloads outputs, requires confirm_cost in live mode, and explains that reusing plan_id resumes the job rather than creating a new one. This is rich, non-obvious context that helps the agent predict side effects.

  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 dense, front-loaded sentences with no filler. Every clause adds operational value, and the most important usage constraint (confirm_cost) appears early.

  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?

  The description covers lifecycle, cost confirmation, and idempotency, which are the key operational concerns. It does not define 'live mode' or specify what the return value contains, but given the annotations and sibling tools, the definition is still sufficiently complete for correct invocation.

  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?

  The schema already covers output_dir and confirm_cost, but plan_id and timeout_seconds lack descriptions. The description does add plan_id reuse semantics and confirm_cost requirements, yet it does not explain timeout_seconds or how output_dir interacts with the plan's existing output directory. With 50% schema coverage, this is adequate but not fully compensating.

  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: execute a previously quoted product-visual plan, wait for the stored job, and download outputs. This clearly distinguishes it from siblings like seeany_plan_product_visual, which would create the plan rather than execute it.

  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 phrase 'previously quoted product-visual plan' clearly implies this tool is used after quoting/planning, and the resume behavior adds important context. It does not explicitly name alternatives or state when not to use it, so it falls just short of a 5.

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