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

With no annotations, the description carries the full behavioral burden and does not deliver: it says nothing about side effects, whether it waits for the element, what happens on multiple matches or a missing element, or how the three targeting options interact. 'Clicks' is a mutating action, so these omissions matter.

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?

A single front-loaded sentence naming the action and its three targeting options with zero padding. Nothing could be trimmed without losing information.

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 or annotations exist, and the description stops short of covering failure behavior, waiting, or the fact that all three params are optional (what happens if none is supplied). Adequate for identifying the tool but incomplete for invoking it confidently.

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 three parameters are already documented in the schema; the description merely restates selector/text/aria-label. It adds no precedence, mutual-exclusivity, or fallback semantics beyond what the schema provides, so the baseline 3 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?

States a specific verb (clicks) and resource (element in the page) plus the three targeting mechanisms, which is enough to distinguish it from the read/navigation/inspection siblings. However it never names or contrasts a sibling, so differentiation is inferred rather than stated.

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?

There is no when-to-use, when-not-to-use, or prerequisite guidance at all. An agent must guess that this belongs to a browser-automation workflow and when clicking is preferable to flow_eval_js or flow_execute_prompt.

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 provided, the description carries the full burden of behavioral disclosure. It mentions the execution context ('active page context on your local browser') but omits critical traits such as whether the script can mutate the page, security implications, return value behavior, error handling, or async support for a tool that executes arbitrary JavaScript.

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?

A single, front-loaded sentence with no wasted words. It states the action, the resource, and the execution context efficiently.

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 tool that executes arbitrary JavaScript, the description is insufficient: it does not explain what the script returns, whether it runs as an expression or statement, async handling, or error behavior. With no annotations and no output schema, the description should provide more behavioral context to call it 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?

Schema description coverage is 100% for the single 'script' parameter, which is already documented as 'JavaScript to execute'. The description adds 'custom JavaScript' but no syntax, format, or execution-semantics details beyond what the schema provides. Baseline 3 applies when 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 states a specific verb ('Runs') and resource ('custom JavaScript in the active page context on your local browser'), clearly distinguishing it from click, screenshot, and status siblings. However, it does not explicitly differentiate itself from flow_execute_prompt or flow_inspect_canvas, which also operate on page context.

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?

There is no guidance on when to use this tool versus alternatives like flow_execute_prompt or flow_inspect_canvas, nor any prerequisites or exclusions. The description only states what it does, leaving the agent to infer appropriate 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 provided, so the description carries the full behavioral burden. It reveals a mutation side effect ('triggers generation') and hints at an auth scope ('your personal workspace'), but says nothing about required browser/session state, latency of generation, failure modes, or whether the action is reversible.

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?

A single tight sentence with the action front-loaded and no filler. Nothing could be removed without losing meaning.

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 mutating browser-automation tool with zero annotations and no output schema, the description omits the setup sequence (browser launched, tab opened, logged in) that its sibling tools imply is mandatory. An agent could easily call it in the wrong state.

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 already documents prompt, submit, and selector. The description adds no syntax, format, or selector-override guidance beyond the schema, so baseline 3 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?

States a specific verb and resource: injects a prompt into Google Flow and triggers generation. An agent can distinguish it from generic siblings like flow_click or flow_eval_js, though it never explicitly names or contrasts with those alternatives.

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 when-to-use guidance, no preconditions, and no mention of the relationship to sibling setup steps (flow_launch_browser, flow_open_tab). The agent must infer that the browser and a tab must already exist.

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 behavioral burden. It discloses the content of the response (prompt inputs, action buttons, canvas nodes), which implies a non-mutating inspection, but it never states that it is read-only, requires an active browser/tab, or has any side effects or failure modes.

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?

A single front-loaded sentence with a colon-delimited list of returned artifacts; no filler. It is as short as it can be while still naming the resource and output.

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 the only source of truth, and it only sketches the returned fields rather than their structure or how they map to the canvas. For a no-param inspection tool this is adequate but leaves real gaps about prerequisites and result shape.

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 takes zero parameters, so the schema has nothing to explain and the baseline of 4 applies. The description correctly adds no parameter detail because none exists.

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?

States a specific verb (inspects) and resource (active Google Flow workspace) and even enumerates what it returns. It is clear on its own, but it never distinguishes itself from the closest sibling flow_status, which likely also reports workspace state.

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?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives among the seven flow_* siblings. An agent must infer that this is the read/inspect step versus flow_click, flow_screenshot, or flow_status.

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 of behavioral disclosure. It doesn't say whether launching replaces or attaches to an existing browser session, what the default lifecycle is, whether authentication state persists, or what happens if the debug port is already in use.

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?

A single sentence with no filler, and the mode distinction is front-loaded. It is efficient, though it could have spent the same length on more useful behavioral 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?

For a session-launching operation with no annotations and no output schema, the description omits critical context: side effects on any running browser, return behavior, and cleanup expectations. The schema covers parameters but the description leaves lifecycle behavior unspecified.

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 port, headed, and targetUrl are fully documented in the schema. The description's headless/headed contrast duplicates the schema's 'headed' description and adds no new syntax, format, or defaulting detail.

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 states it 'controls local browser execution mode' and clarifies the headless-vs-headed distinction, but the verb 'controls' is vague and it never says it launches the browser (as the name flow_launch_browser implies). An agent must infer that this starts/stops a browser session rather than reconfiguring one.

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?

It implies when headed mode is needed ('for 1-time login'), which gives some usage context, but it never states when to call this tool versus siblings like flow_open_tab or flow_status, nor any prerequisites or exclusions.

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 behavioral burden. It hints that the action happens "in your local browser" (a local side effect), but does not say whether an existing tab is reused, whether a window is opened, what happens if the browser isn't running, or whether the call is idempotent.

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?

A single front-loaded sentence with no filler; the action and target are stated immediately.

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 one-parameter, no-output-schema tool the description is minimally sufficient, but it omits ordering/prerequisite context (does a browser need launching first?) and failure behavior, leaving the agent to infer the workflow.

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 single url parameter is fully documented with its default, so the schema already does the work. The description adds no format or override semantics beyond what the schema states, making the baseline 3 correct.

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?

States a specific verb pair ("navigates to or focuses") and a clear resource ("Google Flow in your local browser"), so an agent knows exactly what the call does. It does not, however, distinguish itself from the closely related sibling flow_launch_browser, which an agent would have to resolve on its own.

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 when-to-use guidance is given: nothing says whether this must be called before flow_execute_prompt, or how it differs from flow_launch_browser. The usage context is only implicitly inferable from the tool name.

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 burden. It discloses that the screenshot is of the 'active' workspace and that the browser is a 'local background browser,' which implies no need for a visible browser window. However, it does not state whether the screenshot is saved to disk, returned as data, or how errors (e.g., no active workspace) are handled.

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?

A single, well-formed sentence that front-loads the action and resource. 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?

For a tool with one optional parameter and no output schema, the description is adequate but incomplete. It omits where the screenshot goes (file path, return value) and what happens if no active workspace exists, which are important for correct invocation in a browser automation context.

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% (the single 'filename' parameter has a description), so the baseline is 3. The description adds no parameter-specific meaning beyond what the schema 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?

States a specific verb (Captures) and resource (screenshot of the active Google Flow workspace) with clear scope. The phrase 'in your local background browser' distinguishes it from a hypothetical cloud or remote screenshot tool and aligns with siblings like flow_launch_browser 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.

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

The description implies usage (capturing a screenshot of the active workspace) but gives no explicit when/when-not guidance or alternative tools. A user must infer that this is for visual inspection, perhaps instead of flow_inspect_canvas.

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 burden. It discloses what is inspected (connection, background, login), which implies a read-only diagnostic with no side effects, but it never states that explicitly nor mentions permissions, rate limits, or return format. 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.

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

A single efficient sentence that front-loads the purpose with no filler. It is slightly list-like but every element 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?

For a simple read-only status tool with one optional parameter and no output schema, the description covers what is being checked. Nothing critical to invoking it correctly is missing, though a note on when to use it would round it out.

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 single 'port' parameter is fully documented in the schema with its default. The description adds no additional meaning about the port, so the baseline 3 is appropriate when 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?

States a specific verb ('Checks') and enumerates the resources inspected: browser connection, background status, and Google Flow login state. This makes the diagnostic role clear relative to the action-oriented siblings (launch, click, eval, etc.), though it never explicitly differentiates itself from them.

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 when-to-use guidance, no prerequisites, and no mention of alternatives. The context in which an agent should call this (e.g., before acting, to verify connectivity) is left entirely to inference.

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