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 only restates the click action and the ref source; it does not disclose whether the click waits for navigation, how stale or missing refs are handled, or what side effects occur when clicking (e.g., form submission, navigation, page change).

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 wasted words. The primary action and required input are front-loaded, and the additional tab-targeting capability is mentioned briefly without unnecessary 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?

The description is minimally adequate for an agent to understand what the tool does and how to provide a ref, but it lacks behavioral context such as post-click behavior, error handling, and the agentId routing model. Since there are no annotations and no output schema, the agent is left guessing about side effects and return values.

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 baseline is 3. The description adds minimal semantic value beyond the schema: it reinforces that ref comes from browser_snapshot and that tabId selects a tab, but it does not explain agentId routing, element, or doubleClick behavior beyond what the schema already states.

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 (Click), a specific resource (element via its ref from browser_snapshot), and a key capability (targeting a specific tab via tabId). It is clearly distinguishable from sibling tools like browser_hover, browser_press_key, and browser_type.

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 correct workflow: obtain a ref from browser_snapshot, then use it to click. It also indicates tabId can target a non-active tab. It does not explicitly state when not to use this tool or name alternatives, but its role as the click tool among siblings is fairly unambiguous.

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 reveals non-obvious execution traits: top-level const/let/var declarations persist across calls and the hard 10s timeout, plus the IIFE workaround. These are exactly the kind of details an agent cannot infer from the tool name or schema.

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 compact, front-loaded with the core purpose, and every sentence adds information. The critical caveats (IIFE, no bare return, 10s timeout) are presented immediately after the purpose with no filler 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?

Because there is no output schema and no annotations, an agent is left to infer return values, promise/async handling, and timeout/error behavior. The description covers execution mechanics well, but it does not say what the tool returns or how failures surface, so it is not fully 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?

The schema already describes all three parameters with 100% coverage, so the baseline is 3. The description adds meaningful semantics for the expression parameter: state persistence across calls, the IIFE requirement, the ban on bare return, and the timeout constraint. The tabId mention is useful but largely redundant with 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 first sentence states the action and object clearly: 'Evaluate JavaScript in a page context.' This is specific enough to separate it from navigation, snapshot, and form-filling sibling tools, and the later tabId mention confirms it operates in a browser page.

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 gives clear invocation context (evaluate JS in a page, optionally targeting a tab) and provides crucial rules for correct use: wrap multi-statement code in an IIFE to avoid state leakage, never use bare top-level return, and respect the 10s timeout. It does not name an alternative tool or an explicit 'when not to use', so it falls 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.

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 not explain what happens if a field is not found, whether placeholder values are replaced, whether events are fired, or what the return value is. The only disclosed behavior is the ability to fill multiple fields and target a tab.

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 concise and front-loaded with the core purpose. Both sentences are relevant, though the tabId sentence is somewhat redundant with the schema. It remains efficient with 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 form-filling tool with no annotations and no output schema, the description is too thin. It omits expected return values, error behavior, whether the tool waits for elements, how it interacts with dynamic forms, and any side effects. An agent would lack critical context for reliable invocation.

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 all parameters. The description's statement about tabId support is redundant with the schema, adding no meaningful semantic detail beyond what an agent can read from the input 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 fills multiple form fields at once, which is a specific verb+resource with scope. This differentiates it from siblings like browser_type, which likely targets a single field, though it doesn't explicitly name the alternative.

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 given on when to use this tool versus browser_type, browser_select_option, or browser_click. It only describes a feature (tabId targeting) without any context about prerequisites, exclusions, or typical scenarios.

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 states the action and tab targeting but does not describe side effects like triggering hover states, tooltips, or menu expansions, nor does it mention visibility requirements or whether the hover completes synchronously.

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 short and front-loaded: the core action appears first, followed by the tab-targeting detail. Both sentences are informative and there is no filler, though a brief usage note could be added without harming brevity.

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 hover action, the description plus a fully documented schema is close to minimally viable. However, there is no mention of when hover is useful, what the expected outcome is, or which parameter (ref vs element) is authoritative, leaving some context for the agent to infer.

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 parameters are already fully documented. The description adds only that tab targeting is supported, which duplicates the tabId schema description rather than providing new semantic insight.

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 uses a specific verb ('Hover') and resource ('an element'), making the tool's action unambiguous. It also mentions tab targeting, which helps distinguish it from related browser interaction tools like browser_click or browser_press_key.

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 no guidance on when to use hover instead of alternatives, such as when revealing tooltips or dropdown menus before a click. It does not mention any hover-then-act pattern or conditions that would make hover the appropriate sibling tool.

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 of behavioral disclosure. It only restates the core action and tab default but does not disclose whether navigation waits for page load, updates history, can fail on invalid URLs, or how to confirm completion. This is thin for a page-changing action.

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 filler. It is efficient and readable, though it sacrifices behavioral context for brevity, so it does not warrant a 5.

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 or annotations, the description should explain post-conditions such as page-load waiting, navigation success/failure, and whether to pair with browser_wait_for. It provides none of this, leaving an agent under-informed for a core browser action.

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 all parameters already have meaningful descriptions, including tabId's active-tab fallback and agentId's routing behavior. The description adds no parameter-specific detail beyond the schema, so the baseline score of 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 states a specific verb (Navigate), a resource (URL), and a scope (specified tab or active tab). This clearly distinguishes it from sibling navigation tools like browser_navigate_back, browser_navigate_forward, and browser_reload, which operate differently.

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 explicit guidance is given about when to use this tool versus alternatives. It does not mention that browser_navigate_back/forward are for history navigation, or when active-tab navigation is insufficient. The agent must infer usage from the name and schema.

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 only states the action and does not explain what happens when there is no history, whether the operation waits for page load, or that it mutates the current tab's state. This is a notable gap for a navigation action.

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, direct sentence with no filler or redundant phrasing. It is front-loaded and every word contributes to the 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 low-complexity tool with two optional parameters, the description combined with the schema is minimally sufficient to invoke the tool. However, missing behavior around no-history cases, navigation completion, and return value leaves gaps that would benefit an agent.

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 both tabId and agentId. The description adds no additional parameter semantics beyond the phrase 'specified tab', which only reinforces the existing 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 states a specific verb ('Go back') and resource ('history for the specified tab'), making the operation immediately clear. It also distinguishes itself from siblings like browser_navigate_forward and browser_navigate by the direction of navigation.

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 given about when to use this tool versus browser_navigate_forward or browser_navigate. The description does not mention conditions like needing existing history, nor does it reference alternatives 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?

No annotations are provided, so the description must disclose behavioral traits itself. It only says 'go forward in history' and does not state what happens when there is no forward history, whether navigation waits for page load, or whether the tab must already exist.

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 with no filler and the core action is front-loaded. It is appropriately concise for a simple navigation action, though it could include a small amount of behavioral context without becoming verbose.

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 absence of annotations and an output schema, the description omits important context such as failure behavior, return value, and how it fits into the navigation workflow with siblings like browser_navigate_back. It is minimally complete but relies heavily on inference.

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 baseline of 3 applies. The description adds little beyond the schema, merely reinforcing that the action applies to a specific tab; it does not clarify optionality or agent-routing behavior beyond what is already 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?

States a specific action ('go forward') applied to browser history for a specified tab, which distinguishes it from sibling tools like browser_navigate_back and browser_navigate. Even though the name already implies the direction, the description adds the 'history' and 'tab' context clearly.

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 given about when to use this tool versus alternatives, such as after a back-navigation or when forward history exists. The agent must infer the intended use purely from the tool name and general browser semantics.

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, but it only states the action itself. It does not disclose focus requirements, whether key combinations/modifiers are supported, whether the page might navigate or change, or what the function returns after pressing the key.

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, direct, front-loaded sentence with no filler or redundant wording. It conveys the core action immediately and is appropriately sized for a simple 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?

The definition is complete enough only at a surface level. It lacks important context such as prerequisites (focused element, loaded page), support for modifier keys, potential side effects, and any return/acknowledgment behavior. Since there is no output schema, this behavioral gap is more significant.

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 all parameters well. The description adds no new meaning beyond 'specified tab,' which merely references the tabId parameter. This meets the baseline for fully documented schema parameters.

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?

Describes a specific action ('Press a keyboard key') with a clear target resource (keyboard key) and scope (specified tab). This clearly distinguishes it from sibling tools like browser_click (mouse action), browser_type (text input), and browser_navigate (page navigation).

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 given on when to use this tool versus alternatives such as browser_type or browser_evaluate. It does not mention when not to use it, nor does it explain whether it is intended for shortcuts, special keys, or text entry.

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?

There are no annotations, so the description must fully communicate behavior, but it only restates the action without noting side effects, whether it waits for the page to load, how failures are handled, or that reloading may lose unsaved form state. This is a meaningful gap for a browser action.

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 focused sentence with no wasted words. It immediately conveys the core operation and is appropriately front-loaded.

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?

The tool is simple and its parameters are fully documented, but with no annotations and no output schema, the description provides only the bare minimum. It does not explain post-reload behavior, error conditions, or when the action completes, leaving some ambiguity for an agent.

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 both tabId and agentId are already documented in the schema. The description adds no additional parameter semantics beyond the generic phrase 'specified tab,' which earns the baseline score.

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 clear verb and resource: 'Reload the page in the specified tab.' This is concise and distinguishes the tool from siblings like browser_navigate or browser_snapshot by naming the specific action of reloading.

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 use case is implied: call this when you want to refresh/reload the current page in a tab. However, it does not explicitly state when not to use it or mention alternatives such as browser_navigate or browser_navigate_forward, so the guidance is minimal.

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 and does state that scrolling occurs on a page or element and can target a tab. It does not mention defaults, animation, side effects, or error behavior, but the core operation is transparent for a relatively low-risk action.

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 concise and front-loaded: it states the primary action and target first, then adds the tab capability. There is no filler or unnecessary repetition of schema fields.

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 five-parameter tool with strong schema descriptions and no output schema, the description covers the core concepts adequately. It could be improved by explicitly naming the ref parameter as the element selector and noting default tab behavior, but those are already present in the schema.

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 80%, and the description does not add meaning beyond the schema's own parameter descriptions. The direction enum lacks a description, but the scroll verb plus enum values make the intent clear.

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 action ('Scroll') and identifies two possible targets: the page or a specific element. It also adds tab targeting, making the tool's scope clear. However, it does not explicitly distinguish itself from sibling tools beyond the scroll action.

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 for when to use this tool versus alternatives like browser_evaluate or browser_wait_for. The only usage hint is tab targeting, which describes a capability rather than a decision rule.

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 of behavioral disclosure. It only states the action and tab targeting; it does not mention whether change events are fired, whether the element must be visible or enabled, what happens if the option value is invalid, or whether navigation/state changes may occur.

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 two concise sentences with no filler. The core action is front-loaded, and the tab-targeting capability is stated as a secondary but relevant 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?

The tool is simple and the schema covers all parameters, so the description is adequate for basic invocation. However, with no annotations and no output schema, some behavioral context — such as return behavior or event side effects — is missing, leaving the completeness only at a minimum viable level.

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 all parameters are already documented. The description only reiterates that tabId can target a specific tab, adding no semantic information beyond the schema. 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 action: selecting an option in a <select> element, which distinguishes it from generic interaction tools like browser_click or browser_type. It does not explicitly contrast with sibling tools, but the resource and verb are specific enough.

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?

Usage is implied by the phrase 'Select an option in a <select> element' — an agent can infer this tool is for dropdown option selection. However, there is no explicit guidance on when not to use it or how it relates to browser_click, browser_type, or browser_fill_form.

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 present, the description carries the full behavioral disclosure burden. It honestly warns that refs go stale after DOM changes or navigation, which is a non-obvious and important behavior. It also describes the return concept (page structure with element refs) and tab targeting, providing meaningful behavioral context beyond the bare 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 compact and front-loaded: purpose first, then usage guidance, then the critical stale-ref warning, then the tabId detail. The 'IMPORTANT' flag draws attention to the most safety-relevant behavior. No sentence is wasted.

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?

This is a relatively simple tool with only two optional parameters and no output schema. The description covers what it returns, when to use it, the main caveat, and tab targeting. It doesn't over-explain, and it provides enough context for an agent to invoke it correctly in most workflows.

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 the schema already documents both parameters. The description adds context for tabId by mentioning tab targeting, but doesn't elaborate on agentId's routing semantics beyond what the schema states. This matches the baseline for fully documented parameters.

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 and resource ('Capture accessibility snapshot of a page') and clarifies the key output ('page structure with element refs for interaction'). It also explicitly distinguishes itself from screenshots, so an agent can tell it apart from sibling tools like browser_take_screenshot.

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 gives clear guidance to use this instead of screenshots when locating elements to click/type, and includes a critical staleness warning with a concrete directive to re-snapshot after DOM changes or navigation. It doesn't enumerate all alternative tools or exclusion cases, but the primary decision point is well covered.

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 does state that tabId is returned and can be used to target a tab 'without switching', and it lists close as a supported operation, conveying that the tool can mutate state. However, it does not mention the effects of switching (active tab change), the finality of close, or the behavior of the 'done' action, which are meaningful behavioral traits for an agent to know.

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 filler. The primary capabilities are front-loaded, and the most important cross-tool behavior — using tabId to target tabs without switching — is stated clearly and economically.

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?

The description covers the core purpose, the return value, and the key cross-tool usage pattern. The schema is rich and documents all parameters including agentId and the 'done' action, so the description does not need to repeat those details. It is slightly incomplete in not mentioning index as an alternative to tabId, but the schema already handles that.

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 the baseline is 3, but the description adds real semantic value by explaining that tabId returned from list output can be passed to other tools to target a specific tab without switching. This connects the parameter to its cross-tool usage, which is not fully conveyed by the schema alone.

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 names a specific resource ('browser tabs') and four concrete verbs ('List, create, close, or switch'), making the tool's purpose immediately clear. This distinguishes it from page-level navigation siblings like browser_navigate and browser_reload, which operate within a single tab rather than managing tabs themselves.

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 clearly conveys that this tool is for tab-level operations and explains how the returned tabId can be used with other tools, which gives the agent practical routing guidance. It does not explicitly exclude alternatives or state when to prefer browser_tabs over chrome_windows or browser_navigate, but the operation list implies the appropriate context.

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?

It discloses that screenshot output is not a substitute for element discovery and that capture can target a tab. However, with no annotations, the description leaves implicit what the tool returns, whether the fullPage option is honored by default, and any effects on browsing state. This is adequate for a simple capture action but not fully 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 contain the essential purpose, the sibling routing instruction, and the tab-targeting capability. It is front-loaded and contains no redundant wording.

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 a straightforward screenshot operation and fully documented parameters, the description is nearly complete. The only meaningful gap is the return format or behavior, but this does not prevent a correct call. The sibling routing and tab targeting are covered explicitly.

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 tabId, agentId, and fullPage. The description only reiterates tabId targeting and does not add new parameter semantics beyond what the schema provides. 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 first sentence names a specific verb and resource ('Take a screenshot of a page'), and the distinction from browser_snapshot is explicit: snapshots are for finding interactable elements. This makes it immediately identifiable among many browser siblings.

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 gives a clear exclusion — use browser_snapshot instead when the task is finding interactable elements — while leaving screenshots for visual capture. It also mentions the tabId option for targeting a specific tab, which orients the agent in multi-tab workflows.

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, but it only restates the action and tab targeting. It does not mention whether existing text is replaced or appended, whether the field must be visible or focused, or any side effects of the submit option.

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 short sentences with no filler. The first sentence states the primary action, and the second adds the tab-targeting capability, so every sentence 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?

The schema fully describes all six parameters, which helps, but the description alone leaves gaps around usage versus sibling tools and behavioral side effects. For a tool with no annotations and no output schema, this is 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%, so the baseline of 3 applies. The description adds little semantic value beyond the schema; mentioning 'input element' only reinforces ref's purpose, and tabId behavior is already documented 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 names a specific action (type text) and a clear target (an input element), so the core purpose is unambiguous. It does not explicitly distinguish itself from siblings like browser_fill_form or browser_press_key, though the action is fairly self-contained.

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 given about when to choose browser_type over alternatives such as browser_fill_form or browser_press_key. The only contextual note is tab targeting, which is a capability rather than a usage rule.

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?

There are no annotations, so the description carries the full behavioral burden. It discloses the 10-second per-call cap, the repeated-call pattern, and cautions against blindly retrying with longer waits. It stops short of describing timeout/error behavior or whether text and time parameters combine, but the key behavioral constraints are present.

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 three focused sentences: purpose, duration limit, and failure guidance. Every sentence adds operational value, with the core wait behavior front-loaded and no redundant filler.

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?

The description covers the main operational details an agent needs: what to wait for, max duration, how to handle longer waits, failure advice, and tab targeting. It does not describe the return value or timeout behavior, which is a minor gap given the absence of an output schema, but the description remains adequate for correct invocation.

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 all four parameters. The description reinforces the max-10s rule and tab targeting, but adds little meaning beyond the schema for individual parameters. 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 operation: wait for text to appear or wait a fixed duration. It names the subject (the page), the two supported modes, and is immediately distinguishable from sibling navigation, interaction, and inspection tools.

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 provides clear guidance on how to use the tool: call multiple times for longer waits, avoid blindly increasing wait time on failure, and target a specific tab when needed. It does not explicitly name alternatives, but no sibling tool overlaps with this wait-specific functionality.

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. 'List' and 'installed' imply a read-only, non-destructive operation, which is useful, but the description does not explicitly state side effects, prerequisites, or the structure of what is returned. This is acceptable for a simple read tool but not highly 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 a single sentence that front-loads the action and object. It contains no filler, redundant phrasing, or unnecessary detail, fully earning its place in the definition.

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 takes zero parameters and is a straightforward listing operation, the description provides enough context for an agent to know when to call it. The only minor gap is that it does not specify what fields or details the returned extension list contains, but this is not critical for a zero-argument introspection 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?

The input schema has zero parameters with 100% schema description coverage, so the baseline is 4. No parameter semantics are needed, and the description does not attempt to add any, which is appropriate here.

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 uses a specific verb ('List') and a concrete resource ('installed Chrome extensions'), making the tool's purpose immediately clear. It also distinguishes it from sibling tools like browser_tabs or chrome_windows, which handle different browser aspects.

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 clearly implies when to use the tool: whenever the agent needs the set of installed Chrome extensions. There are no explicit exclusions or alternative tool references, but no sibling tool appears to be a direct alternative, so the context is sufficient.

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 must carry the behavioral burden. It does state the primary behavior: bringing a tab into focus in the browser UI. However, it does not mention side effects such as changing the active tab, potential window focus changes, error behavior for invalid tab IDs, or what the tool returns. For a mutating action, more disclosure would be helpful.

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 the core action front-loaded and a parenthetical clarification. Every word earns its place, and there is no redundant 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?

For a simple one-parameter tool with no output schema, the description plus schema adequately defines what the tool does and where the tabId comes from. It is slightly incomplete because it does not specify behavior for invalid or stale tab IDs, but the overall context is sufficient for an agent to invoke 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%, and the single parameter tabId is described as 'Tab ID to bring into focus (from browser_tabs list)'. This already provides strong semantics. The tool description itself adds no additional parameter meaning, so it earns the baseline 3 for relying on 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 states a specific verb ('Bring'), a specific resource ('a specific Chrome tab'), and clarifies the outcome ('activate it in the browser UI'). It clearly distinguishes this tool from siblings like browser_navigate (which changes the page) and browser_tabs (which lists tabs).

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 when to use this tool: when you want to activate an already-open tab. The schema parameter description adds that tabId comes from browser_tabs list, which gives useful context. However, it does not explicitly mention alternatives, when not to use it, or contrast with navigation 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 carries the full burden of explaining behavior. It discloses that listing shows all windows and their tabs, but it does not describe side effects, permissions, focus behavior, or the response format. The unsupported 'focus a specific window' claim further muddies what the tool actually does.

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 short and front-loaded, with the core list behavior stated early. The generic word 'Manage' and the false focus capability are minor structural flaws, but overall the description is not bloated.

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 one-action tool, the description is mostly adequate: it says the action lists windows and their tabs. But the false focus claim, lack of output details, and absence of guidance about when to prefer this tool over sibling window/tab tools leave meaningful 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% and the sole parameter (action) has a clear enum description in the schema. The tool description adds little parameter-level meaning and even implies a focus action that does not exist in the enum, so it does not improve on 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 identifies the resource (Chrome windows) and the main operation (list windows with tabs), which is helpful. However, it also states the tool can 'focus a specific window,' while the schema only allows action='list', making the stated purpose partially inaccurate.

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 explicit guidance on when to use this tool versus siblings like browser_tabs, chrome_focus, or browser_snapshot. The phrase 'each window groups multiple tabs' implies a window-level view, but no direct comparison, exclusions, or recommended conditions 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?

With no annotations provided, the description carries the behavioral disclosure burden. It conveys that monitoring is stateful and only captures future logs, and that clear removes the captured logs. However, it does not disclose buffer persistence, limits, or the irreversibility of clearing, leaving some behavioral gaps.

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 compact and front-loaded: it leads with the verb and resource, then gives the lifecycle workflow, and closes with a useful analogy. Every sentence earns its place and there is no filler.

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 self-documenting parameter schema and the simple three-action lifecycle, the description plus schema is largely complete for selecting and invoking the tool. It explains the core workflow and the Console-panel equivalence; the main gap is not describing the exact output shape of 'list', but the action enum already says it shows captured logs.

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 all five parameters, including action enum meanings, level filtering, limit, tabId defaulting, and agentId routing. The description adds no substantial parameter-level detail beyond the per-tab scope already implied by 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 states a specific verb ('Inspect'), a clear resource ('browser console'), and a scope ('for a tab'). The analogy 'Equivalent to the DevTools Console panel' helps disambiguate it from sibling devtools tools like devtools_network and devtools_elements.

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 gives an explicit workflow: start monitoring first to capture future logs, then list or clear them. It does not explicitly name alternatives or exclusion criteria, but the intended usage sequence is clear enough to guide an agent.

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 carries the transparency burden. 'Inspect' and the Elements panel analogy accurately convey a read-only operation, but the description does not disclose that computed styles are only included when 'includeStyles' is true, nor does it describe output or error behavior. This is adequate but leaves some gaps.

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, compact sentence that front-loads the core action and resource, then adds a powerful clarifying analogy. There is no redundancy or filler.

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 fully documented parameters and the useful DevTools Elements analogy, an agent has enough context to select and invoke the tool correctly in most cases. It could be more complete by noting the conditional nature of styles or outlining the response shape, but these are minor given the strong analogy and complete schema.

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 every parameter is already documented in the input schema. The description adds no extra parameter-level meaning beyond what the schema provides, so the baseline score of 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 states a specific verb ('Inspect') and a specific resource ('DOM elements and computed CSS styles for a tab'), and 'Equivalent to the DevTools Elements panel' gives a clear mental model. This distinguishes it from sibling tools like devtools_console, devtools_network, and browser_snapshot without needing to inspect their schemas.

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 DevTools Elements panel analogy provides clear, actionable context for when this tool is the right choice. It does not explicitly name alternatives or state when not to use it, but the equivalence is strong enough to imply the intended usage context.

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 behavioral burden and discloses the key stateful behavior: capturing starts, list shows captured requests, and clear empties them. It also states that only future requests are captured. It does not say whether monitoring continues after clear or how long the buffer persists, but the core lifecycle is clear.

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, no wasted words, and front-loaded with the core purpose. The workflow sentence and DevTools analogy each earn their place and make the description immediately scannable.

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?

The description is enough to invoke the tool correctly: it explains the start-list-clear flow and the DevTools analogy compensates for the absent output schema. It does not detail the exact list result shape or whether clear stops monitoring, but those are minor given the strong schema coverage.

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?

All 6 parameters already have descriptive schema entries, including action meanings, defaults, filter options, and agent routing. The prose adds a high-level framing but does not contribute parameter-level detail beyond the schema, so the baseline of 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 opens with a specific verb and resource: "Inspect network requests for a tab." It clearly differentiates from sibling DevTools tools by naming network requests and adding the parallel to the DevTools Network panel.

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 gives a clear workflow: "Start monitoring to capture future requests, then list or clear them." This tells the agent when each action is appropriate, though it does not explicitly name alternatives 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?

No annotations are present, so the description bears the full burden. It discloses that operations can read or write live browser storage, but it omits side effects of set/delete (e.g., altering page state, invalidating cookies/sessions), return behavior, or per-tab isolation. The default active-tab behavior is only in the schema, not the description.

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 short sentences, front-loaded with the core action and resource; the DevTools analogy is a useful orientation and adds no fluff. No word is wasted.

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 6-parameter tool with no output schema and no annotations, a one-line description is insufficient. It lacks return shape for list/get, mutation caveats, and routing guidance against browser_evaluate, leaving an agent to infer important operational details.

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 baseline is 3. The description adds little beyond the schema—it enumerates storage types already covered in storageType and does not explain action/key/value semantics 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?

Description states a clear verb ('Read or write') and a precise resource ('browser storage for a tab') and enumerates localStorage/sessionStorage/cookies, making it distinct from sibling devtools_* and browser_* tools without needing the schema.

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 DevTools Application panel analogy implies the intended use, but the description does not explicitly state when to choose this tool over browser_evaluate or other devtools tools, nor any exclusions. It is implied rather than stated.

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. It discloses that 'rename' automatically mutates both Claude chat and Chrome group, while 'color' and 'detect' only map/read and return /color and /rename commands. This prevents an agent from assuming every action has the same side-effect profile.

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 compact, front-loads the general purpose, and uses a consistent quoted-action structure for the three modes. No sentence is wasted and the detail is proportional to the tool's complexity.

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, the description appropriately states what each action returns ('returns the /color command', 'returns matching /rename + /color commands') and what 'rename' mutates. All parameters are already covered by the schema, and the tool is simple enough that the description leaves no essential calling information missing.

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 documents all three parameters, so the baseline is 3; the description adds value by explaining what each action does with those parameters and gives a concrete example ('fix chrome mcp') for the 'description' field. This goes beyond the schema's terse 'For color: sync theme color' and clarifies the mapping semantics.

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 opens with a specific verb and resource ('Sync Claude session name/color with Chrome tab group') and then defines three discrete actions with distinct outcomes. This clearly differentiates session_sync from sibling browser-navigation and devtools tools, which focus on tab control or debugging rather than Claude-to-Chrome synchronization.

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 establishes a clear context for when to use the tool: whenever the user wants to synchronize Claude session naming or color with a Chrome tab group. It does not explicitly name alternatives or exclusions, but the action-specific guidance ('rename', 'color', 'detect') tells an agent which mode to choose for a given intent.

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