Selenium MCP Server

by pshivapr

Overview Schema Related Servers Score Discussions

TypeScript

Local

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v1.0.0
Disambiguation5/5
Each tool targets a distinct browser action or element interaction, with clear boundaries between similar tools like window switching variants. Descriptions are precise enough to avoid confusion.
Naming Consistency5/5
All tools follow the 'browser_verb_noun' pattern consistently, with snake_case throughout. The naming convention is uniform and predictable.
Tool Count4/5
56 tools is high but justified given the comprehensive scope of browser automation. However, some tools could be combined or removed without loss of functionality.
Completeness3/5
Covers most core browser automation tasks, but notable gaps like alert handling (accept/dismiss) and window handle retrieval are missing. Essential workflows are present, but some important operations are absent.
Average 3/5 across 56 of 56 tools scored. Lowest: 1.7/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 0 commits in the last 12 weeks
- Last stable release on October 12, 2025
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is failing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
This repository includes a glama.json configuration file.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It does not explain the return value, error behavior, or what 'find' does (e.g., scroll, wait, highlight). The timeout parameter hints at waiting, but this is not mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At only three words, the description is too brief and underspecified. While concise, it omits crucial details, making it ineffective rather than efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 3 parameters (including a timeout), no output schema, and no annotations, the description is grossly insufficient. It does not describe the return value, error conditions, or how it interacts with the browser context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the parameters are fully described in the schema. The description 'Find an element' adds no additional semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Find an element' is vague and does not differentiate from the sibling tool 'browser_find_elements' (plural). It lacks specificity about what finding entails (e.g., returning first element, throwing if not found).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like browser_find_elements or browser_wait_for_element. No context on prerequisites or use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It only says 'scroll', without explaining scroll behavior (e.g., origin, units, overflow, animation) or providing any safety/reversibility info.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (4 words) but at the expense of informativeness. It is front-loaded but does not earn its place because it lacks necessary detail for proper tool selection.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity but lack of annotations and presence of sibling scroll tools, the description is incomplete. It omits usage guidance, behavioral context, and parameter semantics enhancements.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions 'X coordinate' and 'Y coordinate'. The description adds no extra meaning (e.g., units, origin, relative/absolute). Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the verb 'scroll' and resource 'to specific coordinates', but it's ambiguous whether coordinates are absolute or relative, and doesn't distinguish from sibling tools like browser_scroll_by_pixels.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like browser_scroll_to_element, browser_scroll_by_pixels, etc. The description is silent on usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It fails to mention that the tool operates on <select> elements, waits for elements, or handles errors like missing options.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
While concise, the description is overly terse and omits critical details. It does not earn its place as it fails to provide value beyond the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of interacting with dropdowns and the lack of output schema, the description should explain that it selects an <option> by its value attribute. It is incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for three parameters. The description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Select dropdown by value' is a tautology of the tool name. It does not clarify that it selects an option by its 'value' attribute, nor does it differentiate from the sibling 'browser_select_dropdown_by_text'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool over alternatives like browser_select_dropdown_by_text. The description lacks any context about selection criteria or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral details such as whether it waits for the element, what happens if the checkbox is already unchecked, or error handling. The description carries the full burden but provides no insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (4 words), but it sacrifices informativeness for brevity. It fails to include any context that would help an agent use the tool correctly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (uncheck a checkbox), the description omits important context like element preconditions, return behavior, and relation to sibling tools. It is incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for all parameters, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Unselect a checkbox' essentially restates the tool name, adding no additional clarity. It does not distinguish from the sibling tool 'browser_select_checkbox' other than the verb.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'browser_select_checkbox'. There is no mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
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 fails to mention any side effects (e.g., page navigation, form validation) or requirements (e.g., element must be a form). The description is simply the verb and resource.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
While extremely short (3 words), it is under-specified. For a tool with 3 parameters, 54 siblings, and no output schema, this brevity sacrifices necessary information. It is not a model of efficient conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (form submission with locator strategies) and lack of output schema, the description is woefully incomplete. It does not explain return value, form interaction behavior, or error conditions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters 'by', 'value', and 'timeout' are already documented in the input schema. The description adds no extra semantic meaning, thus baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Submit a form' clearly states the action and the target resource. While it distinguishes from sibling tools like browser_click or browser_type, it does not elaborate on scope or behavior, which keeps it from a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives (e.g., browser_type plus browser_click). No prerequisites or context for form submission are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavior. It only says 'switch to a different browser window', omitting details like whether the current window is closed, error handling for invalid handles, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and concise, but it lacks necessary detail to be helpful. It is under-informative given the context of multiple sibling tools.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and many similar siblings, the description fails to explain what this tool does differently or what the agent should expect after switching. It is incomplete for effective tool selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the parameter description already explains the windowHandle. The tool description adds no new meaning, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool switches to a different browser window, but it does not specify that it uses a window handle. Given siblings like browser_switch_to_window_by_title and browser_switch_to_window_by_url, the purpose is vague and lacks differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as switch_to_window_by_title or switch_to_window_by_url. There is no context or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as what happens if the element is not found, if the text is empty, or whether it waits for the element. The description is too sparse to inform the agent about side effects or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks any structure or detail. It does not front-load key information about usage or return value. It is functional but minimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 3 parameters and no output schema, the description should at least mention the return value and basic behavior. It only states the action, leaving the agent uninformed about expected output, error conditions, or timeout behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for its 3 parameters, including an enum for 'by'. The description adds no additional semantics beyond the schema, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets the text of an element, which is a specific verb+resource. However, it does not distinguish from siblings like browser_get_attribute, which retrieves a different property, but the purpose is clear enough for a simple read operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as browser_get_attribute or browser_find_element. There is no mention of prerequisites, context, or scenarios where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations and a minimal description, the tool's behavior is unclear. It does not specify if 'select' toggles or ensures the checkbox is checked, what happens if already selected, or any error states.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
While very short, the description is under-specified, lacking essential details. Conciseness should not sacrifice completeness; here it fails to provide sufficient information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is insufficient. It should clarify the tool's behavior, side effects, and when to use it, but it only provides a minimal phrase.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no additional meaning beyond the schema, which already covers 100% of the parameters. The baseline of 3 is appropriate since the schema is self-explanatory.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Select' and resource 'checkbox', distinguishing it from siblings like 'browser_unselect_checkbox' and 'browser_click'. However, it lacks specificity on what 'select' means in the context of a checkbox (e.g., checking it).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'browser_click' or 'browser_unselect_checkbox'. The description does not mention any prerequisites or conditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description fails to disclose behavioral traits such as whether existing text is replaced, if typing triggers events, or how it handles non-interactive elements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short, but it omits important details that could be included without excessive length, leading to under-specification.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the many sibling tools and no output schema, the description should explain return behavior or success/failure conditions, but does not.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers all 4 parameters with descriptions, achieving 100% coverage. The description adds no extra meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Type into an editable field' clearly states the action and target resource, but does not differentiate from sibling tools like browser_key_press or browser_clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like browser_key_press or browser_click, or on prerequisites like element focus or editability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden of behavioral disclosure. It only states the function without detailing whether the call blocks, returns a boolean, throws errors on missing elements, or respects the timeout parameter. Important traits like side-effect-free nature (readonly) are not mentioned, leaving the agent to assume.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at one sentence, which is efficient. However, it is too terse for a tool with no output schema; it omits critical information like return type and behavior. Every sentence should earn its place, and while there is no waste, the content is insufficient for ideal conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and high schema coverage, the description should at least clarify the return value (e.g., boolean) and what 'enabled' means. Without an output schema, the agent has no way to know the return type or possible errors. The description is incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds no extra meaning beyond what is already in the schema (e.g., it does not explain how 'by' and 'value' interact or what timeout does). It meets the minimum but does not enrich parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Checks if an element is enabled' clearly states the action and resource. It uses a specific verb and noun, making the tool's purpose unambiguous. However, it does not distinguish this from sibling element-state tools like browser_element_is_displayed or browser_element_is_selected, which would benefit from explicit differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., element must exist on page), appropriate contexts, or when not to use it. Sibling tools include multiple element checks, and the lack of usage cues forces the agent to infer implicitly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It only states the basic function, omitting key details like: what the tool returns (boolean?), whether it waits for the element (timeout param suggests yes but not stated), and how it handles missing elements or ambiguous 'selected' state for non-interactive elements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it concise. However, it is under-specified; adding a brief note about return type or behavior would improve informativeness without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of an output schema and the tool's simplicity as a boolean check, the description should include the return value (boolean). It also does not explain implications of the timeout parameter. The description is too sparse for an agent to fully understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameters with descriptions, so the baseline is 3. The description does not add any parameter-specific meaning beyond what the schema already provides, but it does not miss anything either.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Checks if an element is selected' clearly states the action and resource. It distinguishes from sibling tools like browser_element_is_displayed or browser_element_is_enabled, which check other states. However, it does not elaborate on what 'selected' means (e.g., for checkboxes or options), leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., browser_element_is_displayed for visibility, or browser_get_attribute for custom attributes). The agent must infer context from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It only says 'Find multiple elements' without specifying behavior on no matches, waiting, or error handling. The timeout parameter is present but not explained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one phrase), which makes it concise. However, it may be too sparse for a tool with three parameters and no output schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (3 params, no output schema), the description is highly incomplete. It does not explain return values, error cases, or how the tool differs from siblings beyond pluralization.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the schema; all parameters are documented in the schema, but the description does not clarify how locator strategies or timeout work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Find multiple elements' clearly states the verb and resource, and the plural 'elements' distinguishes it from the sibling 'browser_find_element'. However, it lacks details about what type of elements or context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. It does not explain that it returns a list, nor does it contrast with browser_find_element for singular cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It fails to explain what focusing implies (e.g., moving keyboard focus, triggering focus events), potential side effects, or requirements like element visibility or interactability.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it is too terse and omits important information that would be expected in a minimal viable description. It earns its place but lacks substance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is incomplete. It does not address return values, behavior under various conditions, or how it differs from similar tools in the same server.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so its parameter descriptions are already informative. The tool description adds no additional meaning beyond what the schema provides, resulting in a baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Focus' and the resource 'a specific element', making the core action explicit. However, it does not differentiate from siblings like browser_click or browser_hover, which also target elements, but the specific action of focusing is distinct enough.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided; there is no indication of when to use this tool over alternatives, no prerequisites, and no exclusions. The description simply states the action without context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavior. It only says 'Press a key', omitting that the key press is applied to the currently focused element and triggers keyboard events.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely brief (7 words) but at the cost of missing critical context. It is not verbose but fails to earn its place by adding value beyond the name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (one param, no output schema), the description still lacks necessary context like required focus state and relationship to siblings. Incomplete for a complete definition.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers the single parameter 'key' with a clear description and examples. The tool description adds no additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'press' and resource 'key on the keyboard'. It is specific but does not differentiate from siblings like browser_type which types a sequence of keys.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like browser_type or browser_select_dropdown_by_text. Agent may not know to use key_press for single key actions like Tab or Enter.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It only says 'navigate' without explaining whether it waits for page load, handles errors, or affects browser state. Essential behavioral details are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely brief (4 words), which is concise but sacrifices necessary detail. It could include more information without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's single parameter, lack of output schema, and many similar siblings, the description is insufficient. It omits behaviors like page load waiting, error handling, and navigation semantics, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the 'url' parameter adequately (100% coverage). The description adds no additional meaning beyond what the schema provides, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action (navigate) and the resource (URL). However, it does not differentiate from sibling tools like browser_open or browser_navigate_back/forward, which also involve navigation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus its many navigation-related siblings. There is no mention of prerequisites, alternatives, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral disclosure burden. It does not mention if it deselects previous options, waits for the element, or requires a <select> element. The input schema includes a timeout parameter, but the description omits any behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only 5 words, which is concise but too minimal. It lacks details such as that the dropdown element must first be located using 'by' and 'value' parameters, and then the option is selected. While not verbose, it misses necessary context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 4 parameters and no annotations or output schema, the description is insufficient. It does not explain the overall workflow (locate element then select option), the supported element types (e.g., <select>), or potential side effects. This leaves gaps for correct agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema coverage is 100% (all parameters have descriptions). The description adds no additional meaning beyond the schema, so it scores the baseline of 3. The description lists the 'text' parameter but doesn't clarify matching behavior (exact match, case sensitivity, etc.).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Select dropdown by visible text' clearly states the action (select) and resource (dropdown) and distinguishes from sibling 'browser_select_dropdown_by_value' by specifying the selection criterion (visible text). However, it could be more explicit about the element type and selection mechanism.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the sibling 'browser_select_dropdown_by_value' or other dropdown-related tools (e.g., browser_click followed by option selection). This leaves ambiguity for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral traits such as whether cookies are overwritten, permissions needed, or side effects, which is critical for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, but it only restates the tool's name without adding value. While concise, it could be restructured to include more useful context without increasing length significantly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of sibling cookie tools and no output schema, the description lacks completeness for an agent to understand when to invoke this tool or what to expect, hindering correct selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the 'cookie' parameter with an example; the description adds no additional meaning beyond what the schema provides. Schema coverage is 100%, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Set a cookie in the browser' clearly states the verb (Set) and resource (cookie), but does not differentiate from sibling tools like browser_add_cookie_by_name, missing a chance to clarify the unique purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like browser_add_cookie_by_name or browser_get_cookie_by_name, leaving the agent without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry full behavioral disclosure. It does not explain what happens if the cookie already exists (overwrite? error?), persistence, or any side effects. The description merely states the action without behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise at 6 words. It effectively communicates the basic action, but lacks structure or additional context that could be included without harming conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity, the description is minimal. It does not mention return value, error handling, or relationship to similar tools like browser_set_cookie_object. The sibling list shows many related tools, but the description provides no guidance on when this specific tool is appropriate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so parameters are already documented. The tool description adds no additional meaning beyond the schema. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it adds a cookie to the browser. However, it does not differentiate from sibling 'browser_set_cookie_object' which likely serves a similar purpose. The name 'by_name' suggests a simple add by name and value only, but this is not explicitly stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines provided. It does not specify when to use this tool versus alternatives like 'browser_set_cookie_object', nor does it mention prerequisites such as needing a page loaded.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 merely states the action without covering potential side effects (e.g., event triggers), element type restrictions, or what happens after clearing. The timeout parameter is already in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that directly states the tool's purpose with no wasted words. It is appropriately sized for a simple action, though slightly more context could be included without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is too brief to fully guide an agent. It lacks details on return values (none), required element state, or post-clear behavior, leaving the agent to infer based on the name and schema alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All parameters have descriptions in the input schema (100% coverage). The tool description adds no extra meaning beyond the schema's parameter descriptions, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Clears the value of an input element' is clear and specific, indicating the verb (clear) and resource (input element). However, it does not distinguish from sibling tools like browser_type or browser_delete_cookie, leaving some ambiguity in context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, appropriate scenarios, or when other tools (e.g., browser_type, browser_delete_cookie) might be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must convey behavioral details. It only states 'click' without mentioning waiting behavior, visibility requirements, or scrolling. The timeout parameter implies waiting, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. However, it could benefit from additional context without becoming verbose, hence not a perfect 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the large set of sibling tools and no output schema, the description is insufficient. It does not help the agent understand the tool's specific role or return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds no extra meaning beyond the schema. The baseline 3 is appropriate as the schema already documents each parameter minimally.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (click) and resource (element), which matches the tool's purpose. However, it does not distinguish from sibling tools like double-click or right-click, relying on the name alone.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as double-click or hover. The description lacks context for the agent to decide between similar actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It only states 'Delete cookies' but does not disclose scope (all cookies?), side effects (e.g., session termination), or whether the operation is reversible. For a destructive tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise. However, it lacks critical details that could be added without harming conciseness (e.g., 'all cookies'). It is not overly verbose, but also not optimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should indicate return behavior (e.g., success indication). It also fails to clarify if deletion applies to all cookies or a subset. For a simple tool, it is missing essential context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist (0 params), and schema description coverage is 100%. Baseline of 4 is appropriate since there is nothing to add beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'Delete cookies from the browser' with a clear verb+resource. The plural 'cookies' hints at bulk deletion, distinguishing it from sibling 'browser_delete_cookie' (singular). However, it does not explicitly specify 'all cookies' or allow parameter selection.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives like browser_delete_cookie (singular) or browser_get_cookies. The description fails to mention context such as 'use to clear all cookies' or 'use when you need to remove entire cookie store.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 'Perform drag and drop' without mentioning how the action is simulated (e.g., native mouse events), whether elements must be in viewport, or what happens if the target is invalid. This is insufficient for an agent to understand side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (6 words) and front-loaded with the core action. While it could benefit from slightly more context, it avoids verbosity. A score of 4 reflects that it is efficiently structured but borders on being too minimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of output schema and annotations, the description should compensate with behavioral details (e.g., return value, error conditions). It fails to do so. For a mouse interaction tool, missing prerequisites (drag source must be a valid draggable element) and behavioral nuances make the description incomplete. A score of 2 indicates significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover 100% of parameters (by, value, targetBy, targetValue, timeout), each with clear descriptions. The tool description adds no additional meaning beyond the schema. Per the guidelines, when schema coverage is high (100%), a baseline score of 3 is appropriate. No extra value provided by the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (perform drag and drop) and the resource (between two elements). It is specific enough to differentiate from basic click or hover operations, though it does not explicitly distinguish from sibling tools like browser_hover or browser_click. A score of 4 is appropriate as it provides a clear verb+resource combination.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives. Sibling tools include browser_hover, browser_click, and browser_scroll_to_element, but the description offers no context about prerequisites (e.g., element must be draggable) or scenarios where drag-and-drop is preferred. This lack of usage direction makes it difficult for an agent to select the correct tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden for behavioral disclosure. It only says 'Checks if an element is displayed' without explaining what 'displayed' means (e.g., visible in viewport), the return type (likely boolean), or any side effects. This is minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded. However, it omits important details, but that is a completeness issue rather than conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the return value, the definition of 'displayed', or handling of timeouts or errors.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters are well-described in the schema. The description adds no additional meaning beyond the schema, so it meets the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks if an element is displayed, using a specific verb and resource. However, it does not differentiate from sibling tools like browser_element_is_enabled or browser_element_is_selected, which check other states.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives, nor does it mention prerequisites or context for correct use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must reveal behavioral traits. It indicates execution in page context but omits critical details like potential side effects (e.g., modifying DOM), security restrictions, or typical error behavior. More transparency is needed for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is front-loaded with the main action and context, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should indicate what the tool returns (e.g., script result). It does not mention return values, error handling, or timeouts. For a versatile tool like script execution, more completeness is expected.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema fully describes the script parameter. The description adds that execution occurs 'in the context of the current page', which provides context beyond the schema. However, it does not clarify expected input format (e.g., return value handling) or syntax specifics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (execute JavaScript) and the context (current page), which helps distinguish it from other browser actions like clicking or navigating. However, it could be more specific about the scope, such as access to page resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus other sibling tools like browser_click or browser_type. An agent would need to infer that this is for custom scripting, but explicit when-to-use or when-not-to-use instructions are missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should disclose behavioral details. It merely states 'get' (a read operation) but does not specify return format, behavior if cookie is missing, or any side effects. This is insufficient for safe and correct invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of a single phrase. While efficient, it sacrifices necessary detail. It does not waste words but loses points for under-specification.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one parameter, but without annotations or output schema, the description fails to cover behavior for edge cases (e.g., missing cookie), return structure, or error handling. This leaves the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with the single 'name' parameter described. The description adds no further detail beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get a cookie by name' clearly states the action and resource. The tool name and sibling tools (e.g., browser_get_cookies, browser_delete_cookie) further clarify its specific purpose, so it is well-differentiated despite no explicit sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like browser_get_cookies or how to handle non-existent cookies. The absence of any context for proper usage leaves ambiguity for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fails to disclose behavioral traits such as whether it reads from the current page context, what happens with no cookies, or if it modifies state. It only states the action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise at three words, but may sacrifice clarity for brevity. Could benefit from specifying scope (e.g., 'current page') without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema or annotations, the description omits essential context about return format, error handling, or usage conditions, making it incomplete for an AI agent to rely on.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the description correctly implies that no input is needed. The word 'all' adds semantic value beyond the empty schema, confirming the tool retrieves every cookie.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get all cookies' clearly states the action and resource, distinguishing it from sibling tools like browser_get_cookie_by_name which targets a specific cookie.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like browser_get_cookie_by_name or browser_delete_cookies, nor any context about prerequisites or side effects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does not specify behavioral details like whether the screenshot captures the visible viewport or the entire page, file format, or scrolling behavior. This is a significant gap for an agent invoking the tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It is front-loaded with the action. However, it may be too minimal, lacking details that could be added without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one optional parameter, the description is adequate but not complete. It does not clarify output format (return value if no outputPath), or any side effects. The lack of an output schema increases the need for description completeness, which is not fully met.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with one parameter (outputPath) fully described in the schema. The description adds no additional meaning beyond what the schema already provides. Baseline score of 3 is appropriate since the schema covers the parameter adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Take a screenshot' and the resource 'current page', making the action obvious. It distinguishes from sibling tools like browser_click or browser_navigate, but doesn't explicitly differentiate from potential similar tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use or when-not-to-use guidance is provided. The description does not mention alternatives or prerequisites. For a straightforward tool, minimal guidance is acceptable, but some context about capturing visible area vs. full page would help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the basic action. It does not disclose behavioral traits such as allowed pixel ranges, animation behavior, or side effects like scroll events being triggered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of a single sentence that directly states the tool's purpose. It is front-loaded and contains no extraneous information, though it may be too brief.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is minimal and does not cover expected behavior such as scrolling direction, boundary handling, or the possibility of negative values. Given the complexity of scrolling and the lack of annotations or output schema, more detail is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides full description for both parameters (x and y pixel offsets). The tool description adds no additional meaning beyond what the schema conveys, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Scroll by a specific number of pixels', identifying the action and resource. It distinguishes from sibling scroll tools like browser_scroll_to_top or browser_scroll_to_element by specifying pixel-based scrolling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like browser_scroll_to_coordinates, browser_scroll_to_element, or browser_scroll_to_bottom. The description does not indicate prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must cover behavioral aspects. It does not disclose what happens if no window matches the URL, whether it can match partial URLs, or any side effects. This is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise—single sentence that directly states the tool's function. No unnecessary words, but lacks depth.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity, the description could still be more complete. It omits expected behavior like error handling when no window matches, or the possibility of multiple matches. Sibling tools with similar complexity often have more detailed descriptions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage for the 'url' parameter with a clear description. The tool description does not add additional meaning beyond stating the method of switching.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states action and method (by URL). Distinguishes from sibling tools that switch by title or index, but relies on name for differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like browser_switch_to_window_by_title or browser_switch_window_by_index. Missing context on prerequisites or appropriate scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the burden. It only states 'switch' without disclosing if it's destructive, requires focus, or returns any status. The behavior is under-specified for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It efficiently conveys the core action, though it could benefit from additional context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one param, no output schema), the description lacks context about how to obtain the window index, whether it's 0-based, and what happens after switching (e.g., focus change).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'index' is fully described in the schema with coverage at 100%. The description adds no extra meaning 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.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (switch) and resource (window by index), distinguishing it from sibling tools that switch by title or URL. However, it could be more precise by noting the index refers to the order of open windows.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like browser_switch_to_window_by_title or browser_switch_to_window_by_url. No exclusions or prerequisites provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'wait for an element to be present' without explaining polling behavior, timeout effects, or return value. Critical details are missing for effective usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no redundant words. It efficiently states the core purpose, though it could benefit from a bit more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is too brief. It fails to explain what happens on timeout, return value, side effects, or interaction with page state. More context is needed for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage with descriptions for all three parameters (by, value, timeout). The tool description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Wait for an element to be present' clearly states the action and resource, distinguishing it from sibling tools like browser_find_element or browser_click. It conveys a waiting behavior, but could be more specific about the outcome (e.g., success/failure).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives (e.g., browser_find_element, browser_element_is_displayed). The agent is left to infer the appropriate context, which is insufficient for a complete selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states the action without mentioning that it is a read-only operation, whether the page must be loaded, or the format of the returned source. This leaves important behavioral traits unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence that directly states the tool's function. It is appropriately concise but could be slightly more descriptive to include key details expected by an agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having no parameters and a simple purpose, the description is incomplete. It does not indicate the output format (likely HTML string) or any preconditions (e.g., page must be navigated). With no output schema or annotations, the description should provide this context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, and description coverage is trivially 100%. With no parameters to document, the description adds value by confirming the tool requires no additional input. According to guidelines, 0 params sets a baseline of 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and resource ('current page source'), clearly indicating the tool returns the raw HTML of the page. However, it does not differentiate from similar siblings like browser_get_element_text or browser_get_attribute, which retrieve specific parts of the page.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For example, if the agent needs a specific element's text, browser_get_element_text is more appropriate. The description lacks any usage context or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states the action, omitting details like whether it waits for element visibility, triggers events, or moves mouse pointer.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (4 words), but lacks structure. It is not verbose, yet could be better organized with more relevant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete. It does not explain preconditions (e.g., element visibility) or postconditions (e.g., tooltip display).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so parameters are already well-documented. The description adds no additional meaning beyond what the schema provides, meeting baseline expectations.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Hover over an element' uses a specific verb and resource, clearly distinguishing it from sibling tools like click, double_click, or focus.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use hover versus alternatives (e.g., click for interaction, focus for keyboard events). The description provides no usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose any behavioral traits such as effect on other windows, whether it triggers fullscreen or just expands, or any side effects. The description is tautological with the tool name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise (4 words, one sentence). Front-loaded. However, it is so minimal that it might be considered under-informative, but still earns its place without verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no parameters and no output schema, the description is adequate but lacks clarification on what 'maximize' entails (e.g., fullscreen or just maximum size) and any preconditions. Missing context for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has zero parameters (100% coverage), so the description adds minimal meaning beyond the name. Baseline of 4 applies per rules, but description adds no new semantic value, warranting a slight reduction.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action 'maximize' on the resource 'browser window', which is specific and distinguishes from sibling tools like browser_resize (set dimensions) and browser_open (open new window).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., browser_resize, browser_fullscreen if existed). Does not mention prerequisites (window must be open) or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully disclose behavioral traits. It does not explain what happens if already on default content (likely a no-op), nor does it mention that it resets the current browsing context for subsequent commands. This lack of detail limits transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence. It is appropriately short for a simple action, but it could be more informative without added length (e.g., adding 'main page' for clarity).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that the tool is a context switcher with no output schema and no annotations, the description should explain its effect on the browser session. It fails to mention that it is used to exit frames or that it returns to the top-level document, leaving agents to infer from the name alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters and 100% schema coverage, the description does not need to add param details. The baseline is 4 for a parameterless tool. It offers no extra meaning, but none is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Switches to the default content' clearly indicates the action and resource, and the name combined with sibling tools (e.g., browser_switch_to_frame) strongly suggests it reverts to the main page context. However, it lacks explicit mention that 'default content' refers to the main document, which prevents a top score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like browser_switch_to_parent_frame or browser_switch_to_frame. The description does not mention typical use cases (e.g., after navigating into a frame) or exclude inappropriate scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states the action without disclosing side effects (e.g., does it trigger blur events? what if element is not focused?). Minimal behavioral insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with action. Very concise but at the cost of missing context; however, it is not verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool with three parameters and no output schema, the description lacks context about browser behavior, when to use, or prerequisites. Incomplete for effective tool selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so description does not need to explain parameters; it adds no extra meaning beyond the schema, which already describes 'by', 'value', and 'timeout'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Remove focus from a specific element' is a specific verb-resource pair, clearly distinguishing from the sibling 'browser_focus_element' which adds focus.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like 'browser_focus_element' or when removing focus is appropriate. Lacks context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description is minimal. It does not disclose what happens if the cookie does not exist, prerequisites (e.g., loaded page), or side effects. For a mutation with no annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single sentence, concise and front-loaded with no extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool with one parameter and no output schema, description is minimal but arguably adequate. However, it lacks context about deletion scope (single vs all) and behavioral details, making it only moderately complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter 'name'. Description adds no extra meaning beyond schema, but is not harmful. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Delete' and resource 'cookie from the browser'. However, it does not distinguish from sibling tool browser_delete_cookies which deletes all cookies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like browser_delete_cookies or browser_add_cookie_by_name. Agent is left to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description does not disclose behavioral details such as whether resize affects viewport, outer vs inner window, or triggers layout changes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but overly minimal. It states the obvious without added value, failing to fully earn its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple two-parameter tool with no output schema, but lacks context on what exactly 'resize' entails (e.g., window dimensions vs viewport).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both parameters with descriptions (100% coverage). Description adds no additional meaning beyond what the schema provides, earning baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses specific verb 'Resize' and resource 'browser window', clearly stating the tool's function. It distinguishes from sibling 'browser_maximize' as resizing is an explicit dimension change.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use resize versus maximize or other window-related tools. No context on typical use cases, prerequisites, or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the action but does not disclose behavioral details like whether a context menu appears, if it waits for the menu, or any side effects. This leaves significant gaps for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. It is front-loaded, but could be slightly more structured for clarity. Still effective and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, the description is minimal. It lacks information about prerequisites (e.g., element visibility), return values, or potential exclusions. Without annotations or output schema, it feels incomplete for reliable agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the parameter descriptions in the schema already explain locator strategy, value, and timeout. The tool description adds no extra meaning beyond the schema, warranting the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: performing a right click (context click) on an element. This distinguishes it from sibling tools like browser_click, browser_double_click, and browser_hover, providing a specific verb and resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use right-click vs other click actions. Among many click-related siblings, an agent lacks context for selection, such as when a context menu is needed versus a standard click.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether scrolling is smooth, instant, or waits for dynamic content. The tool's side effects (e.g., triggering lazy loading) are not mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with one sentence that directly states the action. It is front-loaded and contains no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain return values or side effects, but it does not. It also lacks information about dynamic behavior or page state, making it incomplete for a tool with no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is effectively 100%. The description adds no parameter info, but since there are none, the baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool scrolls to the bottom of the page. It differentiates from siblings like scroll_to_top and scroll_by_pixels, though the differentiation is more implicit from the name than the description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as scroll_to_element or scroll_by_pixels. No context about prerequisites or typical use cases is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only states the action. It does not explain scroll behavior (smooth/instant), element findability requirements, timeout consequences, or what happens if element not found. This lack of detail limits understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise at 4 words, with no fluff. While it is minimally structured, the front-loaded purpose is clear. A slightly more structured description could improve clarity without adding much length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is incomplete for a tool with multiple siblings and 3 parameters. It lacks information on return value (no output schema), behavior on failure, and integration with the locator parameters. Given the complexity, more detail is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema; it does not mention parameters or explain how they are used together. However, it does not contradict the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Scroll to an element' clearly identifies the action (scroll) and target (an element). It distinguishes this tool from sibling scroll tools (e.g., scroll_by_pixels, scroll_to_bottom) which have different scroll behaviors or destinations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like browser_scroll_by_pixels or browser_scroll_to_bottom. Given the presence of multiple scroll-related siblings, explicit usage criteria would help an agent decide correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description does not disclose behavior beyond the action, such as error handling, waiting, or that timeout parameter controls wait duration.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no unnecessary words. However, it could be slightly expanded to include value-add information without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With many sibling tools and no output schema, description lacks essential context such as that switching persists until reverted, or that the element must exist for a successful switch.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage for parameters, so description adds no extra meaning. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action ('switches') and target ('iframe element'). It distinguishes from sibling tools like browser_switch_to_default_content and browser_switch_to_parent_frame.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., browser_switch_to_default_content). No mention of prerequisites or postconditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description does not disclose behavior like matching criteria (exact vs partial) or error handling when title not found.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise but borderline under-specified; lacks any structuring or additional context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter, it vaguely covers the purpose but misses behavioral expectations like match type.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. Description merely restates the parameter (by its title) without adding meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states action (switch), resource (window), and parameter (by title). Distinguishes from siblings like by_url or by_index.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives such as browser_switch_to_window_by_url or browser_switch_window_by_index.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks any behavioral details such as required element state or error conditions. It only states the action without operational context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, efficient and to the point. Could be expanded slightly without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple action tool with well-described schema parameters. However, it omits mention of element visibility or interaction prerequisites.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage for all 3 parameters, so baseline is 3. The description does not add any parameter-specific semantics beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Perform double click on an element', specifying the action and target. It distinguishes itself from sibling tools like browser_click and browser_right_click.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use double click versus alternatives. Description does not provide context or prerequisites for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose any behavioral traits such as what happens when there is no forward history, or whether it triggers an error.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, short sentence with no redundant information. It is appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no parameters and no output schema, the description is adequate but lacks details on edge cases and behavioral context, making it minimally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, and the schema coverage is 100%. The description adds no additional parameter-level semantics, but this is acceptable given no parameters exist. Baseline 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'navigate forward' and the resource 'browser', distinguishing it from siblings like 'browser_navigate_back' and 'browser_navigate'. However, it lacks specificity about the context of forward navigation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor any prerequisites (e.g., needing prior backward navigation).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral details such as what happens if there is no parent frame, or any side effects. The description is too minimal to convey necessary behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of a single clear sentence with no wasted words. It efficiently communicates the tool's function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description is somewhat adequate but misses crucial context about behavior and usage relative to siblings. It lacks guidance on edge cases or prerequisites, leaving completeness moderate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the input schema coverage is 100% trivially. The description adds no parameter details because none are needed, meeting the baseline for zero parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Switches to the parent iframe', with a specific verb and resource. However, it does not differentiate from similar sibling tools like browser_switch_to_frame or browser_switch_to_default_content, which could lead to confusion about when to use each.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., browser_switch_to_frame or browser_switch_to_default_content). The description lacks context for appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits like whether it opens a new window/tab, what happens if a session already exists, or permissions needed. The description is too minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words, but it is under-specified for the tool's context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not explain what a browser session entails, how to use it with other tools, or what is returned (no output schema). It lacks essential context for an AI agent to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for both parameters, so the description adds no extra meaning. Schema description coverage is high, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool opens a new browser session, distinguishing it from sibling tools that operate on an existing session.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lacks explicit guidance on when to use this tool, such as prerequisites or context that it must be used before other browser actions. It is implied but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only says 'Gets the value' without explaining behavior when attribute is missing, waiting semantics, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, 8 words, no unnecessary details. Perfectly concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no description of return value or behavior (e.g., what if attribute not found). Lacks completeness for a getter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All parameters have schema descriptions (100% coverage), and the tool description adds no additional insight beyond those.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets an attribute value from an element, distinguishing it from siblings like browser_get_element_text or browser_get_cookie.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use vs alternatives, but the name and description imply it's for reading a specific attribute, not text or cookies.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral traits. It does not disclose that the element must be a file input, whether it waits for the file dialog, or if it supports multiple files. The description is minimal and lacks transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no unnecessary words. Every word earns its place, making it highly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no output schema, 4 parameters), the description is minimally complete. However, it lacks details on return values, error handling, or result indicators. For a straightforward upload action, it suffices, but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema, such as clarifying that filePath must be absolute or how the by/value work together. It does not enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Uploads a file using a file input element' clearly states the specific verb (upload), resource (file), and context (file input element). It distinguishes itself from sibling tools like browser_click or browser_type which do not handle file uploads.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no explicit guidance on when to use this tool versus alternatives. While the purpose implies it's for file uploads, there is no mention of prerequisites, nor does it exclude cases like drag-and-drop upload. Sibling tools are not referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description does not disclose behavioral traits such as caching behavior, side effects (e.g., discarding unsaved changes), or state changes, which are important for a page refresh operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words, but it could potentially benefit from slightly more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output-schema tool, the description adequately states the action. However, it omits any context about side effects or post-condition state, which would be useful for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has zero parameters with 100% coverage; description adds no new parameter meaning, but the baseline for 0-parameter tools is 4 as per guidelines.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Refresh the current page' uses a specific verb (refresh) and resource (current page), clearly distinguishing it from sibling navigation tools like navigate_forward or navigate_back.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives; no mention of exclusions or prerequisites. The description is purely functional.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It only states that it switches to the 'original' window, but does not explain what happens if there is no original window, whether it closes the current window, or if it works only after opening a new window. This is insufficient for a tool that likely has side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no unnecessary words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters, no output schema), the description is minimally adequate. However, it lacks context about when this tool is useful, such as the need to have previously switched to another window. The description could be more complete without being verbose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, so the baseline score is 4 per the rubric. The description does not need to add parameter information, and it does not mislead. No additional semantic value is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: switching back to the original browser window. It uses a specific verb ('switches') and resource ('original browser window'), which distinguishes it from sibling tools like browser_switch_to_window or browser_close.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. For example, it does not mention that a previous window must exist, or scenarios where this tool is preferred over other window-switching tools. This lack of context may lead to misuse.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states the basic function without detailing any behavior such as error conditions, requirements (e.g., page must be loaded), or that it returns a string. This is insufficient for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: a single sentence of five words. It is front-loaded with the essential information and contains no extraneous content. Every word serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description is mostly adequate. It clearly states what the tool does. However, it could be slightly more complete by explicitly mentioning that the return value is the URL string, though this is implied. Overall, it covers the necessary context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters and 100% coverage. With no parameters, the description does not need to add parameter information, and the baseline score is 4. The description does not attempt to elaborate on parameters, which is acceptable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get the current page URL'. It specifies the verb ('Get') and the resource ('current page URL'), and it differentiates from sibling tools like browser_title and browser_get_page_source, which retrieve other page properties.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. However, the purpose is straightforward, and usage is implied: use it when you need the current page URL. There is no mention of when not to use it or alternative tools for similar tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description 'Close the current browser session' implies termination but does not disclose side effects like state loss, window closure, or session cleanup.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff, perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with no parameters and no output schema. The description fully covers its purpose and is complete for this context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, and schema coverage is 100%. The description adds no parameter info, but baseline for zero params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'close' and resource 'current browser session', clearly distinguishing it from sibling tools like browser_open, browser_navigate, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., browser_switch_to_window, browser_delete_cookies). It does not specify that it should be used to end the session after all tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It states the action but does not mention potential side effects like what happens when no history exists or whether the page reloads.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with no wasted words. It is appropriately sized for the simple action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters, no output schema), the description is minimally adequate. However, it lacks contextual completeness regarding history behavior or edge cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters (input schema is empty), so schema description coverage is 100%. The description adds no parameter info, but none is needed. Baseline for 0 parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Navigate back in the browser' uses a specific verb and resource, clearly indicating the browser back action. It distinguishes itself from siblings like browser_navigate_forward and browser_refresh.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives such as browser_navigate or browser_navigate_forward. Usage is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It accurately describes the operation but adds no extra context like scroll smoothness or page limit effects. The behavior is straightforward, so a 3 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, complete sentence with no unnecessary words. It is optimally concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters, no output schema, straightforward behavior), the description fully conveys what the tool does without additional details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and schema description coverage is effectively 100%. Per guidelines, a baseline of 4 is assigned since there are no parameters to explain.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Scroll to the top of the page'), using a specific verb and resource. It effectively distinguishes from sibling tools like browser_scroll_to_bottom or browser_scroll_to_element.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., scrolling by pixels or to an element). The agent receives no context for choosing this over related scroll tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description clearly states a simple read operation. However, it does not disclose whether the tool waits for page load or how it handles errors (e.g., empty title), though for a getter this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. It is front-loaded and immediately understandable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and no output schema, the description sufficiently conveys the tool's purpose. It could optionally clarify that it applies to the current window/frame, but the current level is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, so no additional semantic information is needed. The description correctly implies no input is required, matching the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('get') and a clear resource ('current page title'), distinguishing it from many sibling tools that perform navigations, clicks, or other actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when the page title is needed, but provides no explicit guidance on when to use this over alternatives like browser_get_url or browser_get_page_source, nor does it mention any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![selenium-mcp MCP server](https://glama.ai/mcp/servers/pshivapr/selenium-mcp/badges/card.svg)](https://glama.ai/mcp/servers/pshivapr/selenium-mcp)

Score Badge

Copy to your README.md:

[![selenium-mcp MCP server](https://glama.ai/mcp/servers/pshivapr/selenium-mcp/badges/score.svg)](https://glama.ai/mcp/servers/pshivapr/selenium-mcp)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pshivapr/selenium-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server