Server Quality Checklist

Tool Scores

• flow_connectB
  3.3/5.0
  Behavior2/5

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

  With no annotations, the description must carry the behavioral disclosure burden. It reveals the connection target and default port, but does not say whether this launches a browser, mutates state, is idempotent, or is required before other operations. This is a meaningful gap for a stateful connect tool.

  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, efficient sentence that conveys the action, target, and default port with no filler. Every piece of information serves the agent's selection and invocation decision.

  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 tool with one optional parameter and no output schema, the description covers the core action and default. However, it lacks behavioral side effects, prerequisites, and any indication of what a successful connection yields, so an agent has only partial context 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 description coverage is 100% and the single parameter 'headless' is fully described with its default and anti-bot rationale. The description itself does not add parameter information, but the baseline of 3 applies because the schema already documents the parameter well.

  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 ('Establishes connection') and a specific resource ('Google Flow Chrome instance on CDP port'), which clearly distinguishes it from sibling tools like flow_disconnect and flow_status. The default port value adds precision.

  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 this tool should be used, whether it must precede the other flow_* tools, or when a sibling like flow_status might be more appropriate. The purpose is implied by the name and description, but explicit usage context is absent.

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

• flow_download_latestB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It does reveal the key trait that it downloads rather than re-generates, but it omits important behaviors such as what happens if no render exists, whether files are overwritten, or how the active project is determined. This leaves significant behavioral ambiguity.

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

  Conciseness4/5

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

  The description is a single, efficient sentence that front-loads the core action and key qualifier. It earns a high score for being concise and readable, though it lacks additional structured guidance that could improve utility without bloating the text.

  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 tool with one optional parameter and no output schema, the description is reasonably complete at a basic level. However, it leaves gaps around the meaning of 'active Flow project' and behavior in edge cases like no rendered asset being available. These omissions make it only minimally viable rather than fully complete.

  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 output_folder as a destination directory path. The description adds no new parameter-level meaning, and the tool description does not clarify whether output_folder is optional or what happens when it is omitted. Baseline 3 is appropriate given full schema 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 clearly states a specific verb ('Downloads'), resource ('most recently rendered image or video asset'), and context ('from the active Flow project'). It also explicitly distinguishes itself from generation tools by adding 'without re-generating,' which sets it apart from siblings like flow_generate_image and flow_generate_video.

  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 phrase 'without re-generating' implies this tool is for retrieving an already-rendered asset, so usage is somewhat clear. However, it does not explicitly state when to prefer this tool over alternatives, nor does it define prerequisites like needing an active project or a prior render.

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

• flow_manage_projectB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the two surface behaviors but does not disclose side effects of creating a project, whether creation is permanent or reversible, permission requirements, or potential failure modes. For a tool with a mutating action, this is a meaningful gap.

  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 that names both capabilities with no filler or redundancy. Every word contributes to understanding the tool's scope.

  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 dual-action tool with no annotations and no output schema, the description is too lean. It does not explain what a 'list' call returns, how naming conflicts are handled on create, or what side effects creation has on the user canvas. The schema covers parameters well, but the surrounding behavior is not fully specified.

  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%, with 'action' having an enum and default, and 'name' explicitly documented as required when action is 'create.' The description adds no additional parameter semantics, but the schema already carries the necessary meaning.

  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 names both distinct actions, 'Lists existing Flow projects' and 'creates a new project,' and identifies the resource and scope ('on the user canvas'). This clearly differentiates it from sibling tools like flow_generate_image, flow_generate_video, flow_connect, and flow_status.

  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 usage through the 'list' and 'create' actions but provides no explicit guidance on when to prefer this tool over siblings or when listing versus creating is appropriate. There are no exclusion criteria or alternative routing, so the guidance is only implicit.

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

• flow_statusA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavior disclosure. It clearly conveys a non-destructive read operation and lists the data points returned. It does not, however, mention whether a connection is required, what the output format is, or any failure/error behavior, so it is adequate but not rich.

  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 sentence that front-loads the verb and resource and packs meaningful detail into a comma-separated list. No words are wasted, and the structure makes the tool's scope immediately readable.

  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 status-check tool with one optional parameter and no output schema, the description covers the essential context an agent needs to decide to invoke it. The main gap is not describing the response structure, but the enumerated data points mitigate that for a low-complexity read-only tool.

  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 documents the single 'full' parameter with 100% coverage, including its type, default, and meaning, so the baseline is 3. The description does not add detail about how 'full' changes the result, but it is not required since the schema already covers the 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 starts with a clear verb ('Checks') and specific resource ('health and telemetry of Google Flow'), then enumerates exactly what is inspected: CDP connection state, active user account, session expiration, and credit balance. This distinguishes it sharply from the sibling generation, connection, and management tools without needing their schemas.

  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 nature of a status/health tool implies when it should be used, e.g., before generating media or after connection issues. However, the description does not explicitly state when to use it versus alternatives or mention any exclusions, leaving usage timing to inference.

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

• flow_disconnectA
  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 full burden and it clearly states the two effects: closing the browser connection and cleaning up MCP state. It does not discuss idempotency or consequences for ongoing operations, but for a simple disconnect tool this is sufficient.

  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, ten words, with the primary action front-loaded. No filler 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?

  For a zero-parameter tool with no output schema and no annotations, the description fully captures the tool's behavior and lifecycle role. An agent can correctly invoke it without additional context.

  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?

  There are zero parameters, so the schema already exhaustively covers them. The baseline for 0 parameters is 4, and the description adds no parameter-specific information, which is acceptable.

  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 ('closes'), a concrete resource ('browser connection'), and the additional cleanup of 'MCP state'. This clearly distinguishes it from siblings like flow_connect and the generation tools.

  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 its role as the shutdown counterpart to flow_connect but never explicitly names alternatives or states when to call it. 'Closes the browser connection and cleans up MCP state' gives context but no when-to-use or when-not-to-use guidance.

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

• flow_generate_videoA
  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 behavioral burden and does so well: it discloses that execution consumes credits, monitors rendering, downloads the MP4, and that the false path avoids credit use. It stops short of stating error behavior or what happens to intermediate state, but the key side effects are visible.

  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 core purpose and model names are front-loaded, and the conditional behavior is packed into a compact, scannable pair of clauses.

  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?

  The description explains the execution flow well and the schema fully documents parameters, but there is no output schema and the description does not state what the tool actually returns (e.g. status, file path, rendering meta). For a 7-parameter generation tool with return-format options, that is a notable gap.

  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 the baseline is 3, and the description goes beyond it by explaining the functional effect of auto_confirm (submission, monitoring, download, credit consumption) rather than repeating the schema's one-line definition. Other parameters remain schema-documented, which is acceptable given full 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 verb and direct object: 'Generates cinematic video clips on Google Flow,' using named models. This immediately distinguishes it from image-generation and connection-management siblings without requiring schema inspection.

  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 delineates the two modes based on auto_confirm: true executes generation, monitoring, and download, while false only prepares a prompt and avoids credit consumption. It does not explicitly name alternative tools for when a still image or a different operation is needed, but the video-specific scope makes that inference straightforward.

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

• flow_generate_imageA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and does disclose non-obvious behaviors: credit consumption only when auto_confirm=true, default no-credit safety mode, reference images attached as chips, and downloaded output location. It does not cover auth, rate limits, or failure behavior, but the key side effects are well stated.

  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 three sentences, with each sentence earning its place: purpose and models, reference-image capability, and the auto_confirm behavior split. It is front-loaded with the core purpose and contains no filler or repetition.

  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 7-parameter tool with no output schema and no annotations, the description covers the central behavioral choices and consequences—safety review, credit consumption, and output destination. It lacks return-value details and does not state whether output_folder is required when auto_confirm=true, but the response_format parameter and schema mitigate these gaps.

  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 the baseline is 3, but the description adds genuine narrative meaning beyond the schema: auto_confirm determines credit use and download, reference_images are described as attachment chips with an example, and output_folder is tied to high-res download. These enrich the structured parameter definitions.

  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 ('Generates high-fidelity images on Google Flow') and lists three concrete model choices, making the resource and output type unambiguous. The word 'images' distinguishes it from the video-generation sibling without needing to inspect the schema.

  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 explicitly explains when to use auto_confirm=true versus false, including credit consumption and UI safety review, giving clear invocation context. It does not explicitly name alternative sibling tools or exclusion conditions, so it stops 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.