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

With no annotations, the description carries the full burden. It describes the action as 'Verify', suggesting a read-only operation, but does not disclose behavioral traits such as what happens on mismatch, error handling, or whether it modifies state. This leaves significant ambiguity for a tool with no structured behavioral hints.

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 a single sentence that is clear, front-loaded, and contains no unnecessary words. It earns its place with direct purpose statement.

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 has no parameters and no output schema, the description is minimally complete for the purpose. However, it does not explain what 'Profile 3' refers to, nor does it describe the return value (e.g., boolean, success/failure message). Additional context would improve completeness for an agent that needs to interpret the result.

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?

The input schema has zero parameters and schema description coverage is 100%, so the baseline is 4. The description does not need to add parameter details, and it successfully implies that no input is required. It adds no extra semantics but does not detract.

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's purpose: verifying that the logged-in Google account matches a configured expected email, specifically mentioning 'Profile 3'. The verb 'Verify' and resource 'Google account match' are specific, making the purpose clear. However, it does not differentiate from sibling tools that might have similar verification tasks, though no such sibling is evident.

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 implies the usage context (checking account match), but it does not explicitly state when to use this tool versus alternatives, nor does it provide when-not guidance. The sibling tools do not include similar verification, so the intended use is inferred but not explicitly guided.

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?

The description discloses that headless mode is not recommended and lists the sequence of actions (launch, connect, navigate, verify). However, it does not mention side effects like opening a visible browser window or potential need for user authentication, which would enhance 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?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose and key actions without extraneous detail.

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, the description should specify what 'verify account' returns (e.g., success, error, connection status). The lack of information about output or side effects makes it incomplete for an AI agent to use correctly.

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?

The input schema already provides 100% coverage with descriptions for both parameters. The description adds value by clarifying the 'headless' default and the profile usage, but does not significantly extend beyond the schema.

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's purpose with specific actions: launching Chrome, connecting CDP, navigating to Google Flow, and verifying account. This effectively distinguishes it from sibling tools like flow_disconnect or flow_status.

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 implies this tool is for initial setup before using other flow tools, but provides no explicit guidance on when to use it versus alternatives, nor when not to use it. A mention of prerequisites or ordering would improve clarity.

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 are provided, so the description must disclose behaviors. It only states 'create', implying mutation, but no details on side effects, authorization needs, uniqueness constraints, or error states. The description is too minimal for a create operation.

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 a single, concise sentence with no redundant information. It is front-loaded with the core action. However, it could be improved by adding context about the optional parameters.

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?

With 5 parameters, no output schema, and no annotations, the description is minimal. It does not explain the role of 'project_name' and 'campaign' in project matching or the expected return value. The description is incomplete for an agent to fully understand the tool's behavior.

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 description coverage is 100%, so the schema fully documents all parameters. The description only mentions 'name and description' and adds no extra meaning for 'reference_images', 'project_name', or 'campaign'. Baseline 3 applies since the schema does the heavy lifting.

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 action ('Create') and the resource ('a new character in Google Flow Characters'). It mentions the required parameters 'name and description'. However, it does not differentiate from sibling tool 'flow_import_character', which likely has a similar purpose.

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?

No guidance on when to use this tool versus alternatives like 'flow_import_character' or 'flow_create_scene'. There is no mention of prerequisites, limitations, or complementary tools.

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 are provided, so the description must disclose behavior. It only says 'create a new scene' without explaining side effects, idempotency, permissions, or success/failure behavior.

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 a single short sentence, which is concise but lacks structure and critical details. It is not well-rounded for the complexity of the tool.

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?

Despite having 4 parameters (all described in schema), no output schema, and no annotations, the description is too brief. It fails to explain return values, error handling, or how to effectively use the tool among 16 siblings.

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 description coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the schema; it merely mentions characters and prompt without elaborating on usage or constraints.

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 'Create' and the resource 'scene', and distinguishes from sibling 'flow_create_character' by specifying scene creation with characters and prompt.

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?

No guidance on when or when not to use this tool, no mention of alternatives (e.g., when to use flow_create_character instead), and no context on prerequisites or use cases.

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 are provided, so the description carries the full burden for behavioral disclosure. It explicitly states that the tool will close the browser and clean up the MCP connection, which is sufficiently transparent about its side effects. It could mention potential data loss risks, but for a disconnect tool 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.

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

The description is a single, front-loaded sentence with no wasted words. Every word is necessary and contributes to understanding the tool's purpose.

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 that the tool has no parameters, no output schema, and no annotations, the description is reasonably complete. It explains the core action. It could benefit from mentioning that this is the reverse of flow_connect, but the sibling names provide that context implicitly.

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?

The tool has 0 parameters and schema coverage is 100% (empty schema). The description adds meaning beyond the schema by explaining what the tool does overall. With no parameters, a baseline of 4 is appropriate, and the description delivers clear context.

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's action: 'Close the browser and clean up the MCP connection to Google Flow.' It specifies the verb 'close' and the resource (browser and connection). Among siblings, flow_connect is the obvious counterpart, so it's well-distinguished.

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 implies usage as the complement to flow_connect but provides no explicit when-to-use, when-not-to-use, or alternative guidance. The context signals show a sibling flow_connect, which gives some implicit context, but the description itself lacks explicit guidelines.

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?

The description discloses the key behavioral trait of updating an internal selectors map for robust automation, which is important for understanding side effects. However, it does not specify authorization needs or potential destructive actions, but the absence of annotations places the burden on the description, which it meets reasonably well.

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 a single concise sentence that front-loads the purpose. It is efficient with no wasted words, but could benefit from a brief structure break for readability.

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 has one required parameter and no output schema, the description adequately covers what the tool does and its main side effect. It would be improved by mentioning the output (e.g., 'Returns the discovered selectors' or 'Updates the map silently').

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% with the page parameter described in the schema. The description does not add any extra meaning beyond the schema, so baseline 3 is appropriate.

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?

Description clearly states the tool navigates to a Google Flow page and discovers interactive elements, with the specific verb 'Navigate' and resource 'Google Flow page'. It distinguishes from sibling tools like flow_open_characters by focusing on discovering UI elements rather than just opening pages.

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 implies use for discovering interactive elements for automation but lacks explicit guidance on when to use this tool versus alternatives like flow_open_characters or flow_open_tools_gallery. No exclusion criteria or alternative suggestions are provided.

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 must clarify behavior. It states 'download' implying a read operation, but fails to disclose what happens if no file exists, whether it's a single download or can be called multiple times, or any 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.

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

Single sentence with clear verb-first structure. Every word is necessary, no wasted content.

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?

For a simple parameterless tool, the description is mostly adequate but omits important context like the possibility of no file, expected return format, and relation to other flow tools. Additional context would improve completeness.

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 zero parameters with 100% coverage, so baseline is 4. The description adds meaning by specifying 'most recently generated', which reduces ambiguity beyond the empty schema.

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 'download' and the resource 'most recently generated file' from 'Google Flow'. It distinguishes from sibling tools like generation tools, but could be more specific about the scope of 'most recently generated'.

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?

No guidance on when to use this tool versus alternatives, nor prerequisites like ensuring a file has been generated. The description lacks context for proper selection.

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?

The description fully discloses behavior: for auto_confirm=false, it fills prompt, selects model/ratio, takes screenshot, returns 'ready_for_confirmation'. For auto_confirm=true, it verifies interface mode, model, takes verification screenshot, then clicks Generate, waits, and downloads. Warns about credit consumption. No annotations to contradict.

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 relatively long but every sentence provides necessary detail. It front-loads the credit warning and uses bullet-like structure with punctuation. Some redundancy could be trimmed, but overall efficient.

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 (8 parameters, no output schema), the description comprehensively covers behavior, prerequisites, side effects (credit consumption), and distinguishes between preparation and execution modes. No gaps.

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 baseline is 3. The description adds credit warning for auto_confirm and context for brand and project_name, but most parameters are already well-described in the schema.

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 it generates images, with specific verb 'generate' and resource 'image'. It distinguishes between two modes (preparation vs. execution) and implicitly differentiates from video generation by mentioning checking for IMAGE mode.

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?

Explicit usage guidance: auto_confirm=false prepares only, no credit consumption; auto_confirm=true executes generation and consumes credits. Also instructs to verify mode is IMAGE, not Video, and that model must be an image model.

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?

With no annotations, the description carries the full burden. It discloses that the tool stops at 'ready-to-generate' and does not execute the paid generation, which is a key behavioral trait. It does not cover rate limits or auth, but the 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.

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

Two sentences with no extraneous content. The first states the purpose, the second provides a critical caveat. Every word earns its place.

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 7 parameters and no output schema, the description covers the essential behavioral context. It could optionally explain project reuse logic, but the schema already describes that. Overall, it provides adequate completeness.

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 baseline is 3. The description adds minimal value beyond summarizing what the schema already provides ('fills prompt, selects Omni Flash or Veo model, configures settings'). No additional parameter meaning is given.

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's action 'Set up a video generation in Google Flow' with specific verb and resource. It differentiates from siblings like flow_generate_image by specifying video generation, and includes a critical behavioral note about not clicking final Generate.

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 note explicitly states what the tool does NOT do (final Generate is a paid feature), guiding appropriate use. However, it does not mention alternatives or when to use siblings, so guidance is slightly incomplete.

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 must disclose behavioral traits. It implies mutation but does not state if it overwrites existing characters, authentication needs, or error handling. The description is too brief to cover these aspects.

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, no redundant words. Front-loaded with action and object. However, it could include more context without losing conciseness.

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 simplicity (one parameter, no output schema), the description is adequate but lacks details on JSON format, validation, success/failure behavior, and contrast with sibling tools.

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 one parameter with minimal description 'Path to character JSON file.' Description adds 'saved JSON file' but no additional details on format or valid values. Schema coverage is 100%, so baseline is 3.

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?

Description clearly states the tool imports a character from a JSON file into Google Flow. The verb 'import' and resource 'character' are specific, and it distinguishes from the sibling 'flow_create_character' which likely creates from scratch.

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?

No guidance on when to use this tool versus alternatives like 'flow_create_character'. No prerequisites, conditions, or scenarios are mentioned.

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?

The description suggests a read-only operation (open and list) but does not explicitly state the absence of side effects or authentication requirements. With no annotations, this is adequate but minimal.

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 a single sentence, efficient and front-loaded with the key action and resource.

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 parameters and no output schema, the description covers the basic functionality. However, it lacks context about prerequisites or expected output format, which could be improved.

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?

There are no parameters, and the schema coverage is 100%. The description is not required to add parameter details, so baseline score of 4 is appropriate.

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's action: opening a specific page and listing existing characters. It effectively distinguishes from sibling tools like flow_create_character and flow_import_character.

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 implies use when you need to view existing characters, but does not provide explicit guidance on when to use this tool versus alternatives like flow_discover_ui or flow_create_character.

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 exist, so the description carries full burden. It does not disclose if the tool is read-only, modifies state, or has any side effects. The phrase 'Open the Google Flow Tools Gallery' suggests a UI action but no details on behavior or requirements.

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 a single, clear sentence with no extraneous words. It is concise and front-loaded, but could be slightly more informative without adding bulk.

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 parameters and no output schema, the description is adequate but minimal. It does not explain 'list available tools' (e.g., whether it returns text or opens a UI) or how this fits with sibling tools. Some context is missing for a complete understanding.

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?

There are no parameters, so schema coverage is 100%. The description adds minimal additional meaning beyond the name, but with zero parameters it is acceptable. Baseline 4 applies.

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 action ('open' and 'list') and the specific resource ('Google Flow Tools Gallery'). It is specific but does not explicitly differentiate from sibling tools like 'flow_discover_ui' which may serve a similar purpose.

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?

No guidance is provided on when to use this tool vs alternatives or any prerequisites. The description lacks context for decision-making, such as whether this tool should be used before other actions.

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 must carry the burden. It implies a read-only operation (checking), which is sufficient. However, it does not disclose any other behavioral traits (e.g., rate limits, 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.

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

Single, front-loaded sentence. Every word adds value; no wasted text.

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?

No output schema, no annotations. Description covers the basic purpose but lacks details on return format, error responses, or prerequisites. Adequate but not complete.

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 description coverage is 100% (history_limit has description). The tool description does not add further meaning beyond what the schema already provides.

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?

Description clearly states verb 'check' and resource 'job queue', listing the components (active, pending, completed, failed). This distinguishes it from siblings like 'flow_status' which likely covers general status.

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?

No guidance on when to use this tool versus alternatives such as 'flow_status' or 'flow_connect'. The description does not specify scenario-based usage.

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 are present, so the description bears full responsibility for behavioral disclosure. It mentions 'current Google Flow page' but does not clarify if the screenshot captures the full page or viewport, whether it is destructive, or any permission requirements.

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 a single, well-front-loaded sentence with no waste. However, it omits potentially useful details, preventing a perfect score.

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?

With no output schema and no annotations, the description is too bare. It does not specify the output format, return value, or any side effects, leaving significant gaps for a simple 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 description coverage is 100% (one parameter with description). The description does not add meaning beyond what the schema already provides, so baseline 3 is appropriate.

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 'take', the resource 'screenshot', and the context 'current Google Flow page'. It is specific and distinguishes this tool from siblings, none of which are screenshot-related.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., other tools for capturing visual output). There are no conditions, prerequisites, or exclusions mentioned.

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?

With no annotations, the description covers key behavioral aspects: it checks multiple status components. It does not mention side effects or authentication, but for a read-only status tool, 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.

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

One sentence, front-loaded with the action and specific items, no wasted words.

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 one optional parameter and no output schema, the description adequately explains the tool's purpose and checks. Minor gap: no mention of return format, but acceptable.

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%, and the schema already describes the 'full' parameter. The tool description adds no extra parameter detail, meeting baseline 3.

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 checks connection status and lists specific items: browser connected, Flow page loaded, account verified, job queue state. It distinguishes from siblings like flow_queue_status and flow_account_check.

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 indicates the tool is for checking current status, but lacks explicit when-to-use or when-not-to-use guidance and does not mention alternatives.

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 are provided, so the description must bear the full burden. It mentions 'open' and 'fill' but doesn't disclose whether this modifies state, requires authentication, or has side effects like creating projects. The behavior of opening an external app (Grid Architect) is hinted but not detailed.

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 extremely concise with two sentences. The first sentence front-loads the core action and settings, the second adds the purpose. No unnecessary words or repetition.

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?

With 8 parameters and no output schema, the description lacks critical context: return value, error handling, prerequisites (e.g., must be in a project), and whether it is idempotent. It mentions 'supports batch shot generation' but doesn't explain the flow or results.

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 description coverage is 100%, so baseline is 3. The description lists several parameters (theme_prompt, shot_prompts, engine, ratio, visual_logic) but misses references, project_name, and campaign. It adds value by framing them as settings for batch generation, but doesn't go beyond the schema's own 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 opens Grid Architect and fills specific settings (theme, shots, engine, ratio, visual logic). It specifies batch shot generation for brand campaigns, distinguishing it from siblings like flow_generate_image that likely handle single images.

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 provides clear context: use for batch shot generation in brand campaigns. While it doesn't explicitly list alternatives or when-not-to-use, the sibling tool names imply single-image generation (flow_generate_image) and generic tool usage (flow_use_tool), giving enough guidance.

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 are provided, and the description does not disclose behavioral traits such as whether opening a tool executes it, requires authentication, or has side effects. The agent is left guessing about the tool's actual impact.

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 a single sentence, which is concise. However, it omits important context that would justify its brevity, making it underspecified rather than efficiently informative.

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 complexity of opening 'any tool' and the lack of output schema or annotations, the description fails to explain return values, execution behavior, or how the tool fits into the overall workflow. It is insufficient for an agent to use reliably.

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?

The input schema has 100% coverage with descriptions for all four parameters, so the description adds little beyond stating that params are optional. The mention of 'optionally fill its configuration parameters' aligns with the schema but provides no additional 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 'Open' and the resource 'any tool by name in Google Flow', and it distinguishes from sibling tools by being a generic tool opener. However, 'open' could be interpreted as merely opening the UI rather than executing the tool, which slightly reduces clarity.

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?

No guidance on when to use this tool versus the more specific sibling tools (e.g., flow_use_grid_architect, flow_generate_image). The description does not specify prerequisites, when not to use it, or alternatives.

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