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

No annotations provided. Description fails to disclose behavior when history is empty, whether it throws errors, or if it blocks execution. Underspecified 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.

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

Single sentence with no unnecessary words. However, could be expanded with parameter details without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity (1 optional param, no output schema), the description should at least clarify the 'wait' parameter and edge cases like empty history. Current text is insufficient for reliable use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Parameter 'wait' has 0% schema description coverage, and the tool description does not explain its purpose or behavior. Agent must infer meaning from name alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action ('navigate back') and resource ('browser history'). It distinguishes from sibling tool 'ie_forward' and 'ie_goto'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use vs alternatives. No mention of prerequisites, history stack state, or comparison with other navigation tools.

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

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

No annotations are provided, so the description fully discloses behavior: it lists and flags ownership with 'mine=true'. It implies read-only operation and does not contradict any expected behavior. However, it lacks details on permissions or performance impact.

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

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

The description is two sentences, front-loaded with the action, and every word is meaningful. No redundancy or verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description explains the return value (list of windows/processes with mine flag). This is sufficient for a list tool with zero parameters, providing complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so baseline is 4 as per guidelines. Schema coverage is 100% since there are no properties. The description adds no parameter info but none is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists all Edge IE-mode windows and IEDriver processes, distinguishing owned vs orphaned. It uses a specific verb 'List' and resource 'browsers', and differentiates from siblings like 'ie_kill_orphans' and 'ie_status'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description explicitly says 'Use to see leftover browsers from prior/other runs', providing a clear usage context. However, it does not mention when not to use or list alternative tools, though the sibling names imply alternatives.

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

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

With no annotations, the description should disclose behaviors. It mentions auto-waiting and selector strategies, but omits side effects (e.g., navigation, state changes), error handling, or return behavior, leaving gaps for a critical interaction tool.

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

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

The description is extremely concise with two front-loaded sentences, no extraneous words, and directly addresses the primary purpose and key parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters, no output schema, and no annotations, the description leaves significant gaps: it does not explain how to combine 'by' and 'value', the role of 'frame', or the effect of 'wait' and 'timeout', which are necessary for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 17%, and the description adds meaning for 'by' (listing selector types) and 'action' (listing click/double/right), but does not explain 'value', 'wait', 'frame', or 'timeout', which are crucial for correct usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'Click an element' and specifies it auto-waits, but it does not explicitly differentiate from sibling tools like ie_hover or ie_press_key, though it mentions action variants (double, right) which provide some distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description does not provide guidance on when to use this tool versus alternatives (e.g., ie_hover, ie_fill) or any prerequisites, leaving the agent without decision context beyond the basic purpose.

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

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

With no annotations, the description carries the full burden. It states that it closes the session and quits the browser, which is transparent about the main effect. However, it lacks details on side effects (e.g., whether unsaved data is lost, if it can be safely called multiple times, or if it waits for pending operations).

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

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

The description is extremely concise, using one sentence to convey the full purpose. Every word is necessary; there is no redundancy. It is front-loaded with the action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, no output schema, and a straightforward action), the description is complete enough. An agent can understand exactly 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.

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 100% (no parameters to describe). The description adds no parameter information, which is acceptable since none exist. Baseline is 4 for 0 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Close the IE-mode session and quit the browser.' It specifies the verb (close) and the resource (IE-mode session and browser), making the purpose clear. However, it does not differentiate from sibling tools like ie_back or ie_forward, but the distinct action of closing is unique enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites (e.g., whether a session must exist) or scenarios where it should be preferred over other tools like ie_kill_orphans.

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

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

Discloses possible actions (accept, dismiss, text, sendkeys) and warns that OS modals may be unreachable. Lacks detail on error cases (e.g., non-existent dialog), but covers key behavior.

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

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

Two concise sentences: first states purpose and actions, second adds important limitation. No redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a simple tool: covers purpose, actions, limitation. Minor omission: no mention of return value for 'text' action, but acceptable without output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage, but description adds significant value: clarifies valid action values, notes default (accept), and explains text parameter usage for sendkeys.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it handles JS dialogs (alert/confirm/prompt) and lists specific actions. Distinct from sibling tools, which focus on navigation, clicks, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Provides context for use: when a dialog appears. Mentions limitation about OS-level modals. No explicit alternatives, but no sibling tool targets dialogs.

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

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

Mentions 'auto-waits' implying the tool waits for the element to be ready, which adds behavioral context beyond the bare schema. However, it fails to disclose whether the field is cleared before typing (the 'clear' parameter exists) or any default behavior.

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

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

Single sentence, no fluff. Efficiently communicates core action. However, given 5 parameters, a bit more detail could be included without harming conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters, no schema descriptions, no output schema, and no annotations, the description is insufficient. The agent lacks information on return values, parameter usage, and edge cases (e.g., frames or clearing).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must explain parameters. It only connects 'text' to the typing action but does not clarify 'by', 'value', 'clear', or 'frame'. The agent cannot infer how to locate the element or use optional parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Type text into an input/textarea element (auto-waits).' This clearly identifies the action (typing text) and target (input/textarea elements), differentiating it from siblings like ie_click or ie_text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool vs. alternatives like ie_press_key or ie_select. The description provides no context for selection criteria.

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

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

No annotations are provided, so the description must disclose behavioral traits. It fails to mention what happens if there is no forward history, whether it waits for page load, or how the wait parameter affects behavior. This leaves critical gaps.

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

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

The description is very concise at one sentence, but it sacrifices necessary detail. It is not overly verbose, but it fails to earn its place by omitting essential context about the wait parameter and behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (one optional param, no output schema), the description should cover prerequisites (e.g., an active browser session) and the effect of the wait parameter. It is incomplete for an agent to judge when and how to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not mention the 'wait' parameter at all. The parameter's purpose (e.g., delay after navigation) remains undefined, adding no value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it navigates forward in browser history, which is a specific verb and resource. It implicitly distinguishes from sibling tools like ie_back (back) and ie_goto (specific URL). However, it could be more precise about scope (e.g., 'one step').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives. For example, it does not clarify that it only works when there is forward history, nor does it differentiate from ie_goto for forward navigation.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool lists frames and returns specific fields, but does not mention read-only nature, side effects, or error conditions. The behavior is implied to be non-destructive, but 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.

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

The description is two sentences with no extraneous text. The main action is front-loaded, and the usage hint is concise. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple listing tool with no output schema and no annotations, the description is fairly complete. It explains what is returned and how to use it. It does not cover error conditions or edge cases, but these are not critical for such a straightforward tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, so schema coverage is 100%. The description adds no parameter information because there are none. Baseline score of 3 is appropriate as the description does not need to compensate for missing parameter docs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists frames/iframes of the current page, specifying the output fields (index, name, id, src). It also distinguishes from siblings by explaining how to use the output with other tools via the 'frame' argument.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description gives explicit usage guidance: 'Use the index or name with the "frame" arg of other tools.' This tells the agent when to use this tool and how to use its output. However, it does not explicitly state when not to use it or provide alternatives.

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

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

No annotations are provided, and the description only states 'Read an element's...' without disclosing behavioral traits such as return structure, multi-element handling, or timing, which are critical for a read tool.

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

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

Two concise sentences with zero wasted words; front-loaded with the action and default behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters, no output schema, and low schema coverage, the description is far too sparse. It fails to explain the selector mechanism ('by' and 'value') or optional parameters like 'frame' and 'limit'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning to the 'attr' parameter (text, value, attribute name), but only 20% of parameters are described in the schema. Required parameters 'by' and 'value' lack any semantic hints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the purpose: reading an element's text, value, or attribute. It distinguishes the tool as a general reader among siblings like ie_text and ie_html, though sibling differentiation is implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives like ie_text or ie_html. The description only specifies how to set the 'attr' parameter without contextual usage advice.

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

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

No annotations are provided, so the description must convey behavioral traits. It only states navigation occurs, but does not disclose whether it waits for page load, error handling on invalid URLs, or the effect of the optional 'wait' parameter.

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

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

A single sentence with no extraneous words, efficient for a simple tool. However, the brevity sacrifices necessary details about parameters and behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with two parameters and no output schema, the description lacks information on return values, side effects, error states, and how the 'wait' parameter affects navigation. It is insufficient for robust agent usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no meaning beyond the parameter names. It does not clarify the format of the URL (absolute/relative), the unit or purpose of 'wait', or any constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Navigate') and the resource ('current IE-mode session to a new URL'). It distinguishes from siblings like ie_back and ie_forward by specifying navigation to a new URL rather than history traversal.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives such as ie_open or ie_back. No prerequisites (e.g., active session) are mentioned, leaving the agent to infer usage context.

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

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

Discloses that it auto-picks the table, returns headers and rows as header-keyed dicts, and is app-agnostic. No annotations present, so description carries full burden; it adequately covers read-only extraction behavior.

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

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

Two concise sentences with no wasted words. Front-loaded with the core purpose, then details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers return format, auto-detection, and app-agnostic nature. Lacks details on error handling or what happens when no grid is found, but overall sufficient for a single-purpose extraction tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the description adds minimal additional meaning beyond the schema. The mention of auto-selection and return format provides some context but does not significantly enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Extract a tabular grid as structured rows' with a specific verb and resource. It distinguishes from siblings by focusing on grid extraction vs general text or HTML retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Provides guidance on auto-picking the table or passing a table_id. Does not explicitly exclude other scenarios, but context is clear.

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

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

No annotations present, and the description only states the action without detailing behavior on error, disabled elements, or scrolling requirements.

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

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

Single sentence is appropriately concise for a simple hover action, but could be slightly expanded for clarity on parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks details on return value, error handling, and parameter semantics, making it incomplete despite the tool's low complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 4 parameters with 0% description coverage; the description adds no explanations for 'by', 'value', 'wait', or 'frame', leaving the agent without guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it hovers over an element, specifically for menus/tooltips, distinguishing it from click 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.

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

The phrase 'for menus/tooltips' gives implicit context for when to use, but lacks explicit guidance on when not to use or alternatives like ie_click.

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

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

No annotations are provided, and the description fails to disclose important behavioral traits such as whether the HTML is rendered or raw, page load requirements, or potential size limits.

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

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

The description is a single sentence with no unnecessary words. It is concise but could be slightly more informative without sacrificing brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema and many sibling tools, the description provides insufficient context for an agent to determine invocation details or expected return format.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, and the description does not explain the meaning or format of the 'frame' or 'limit' parameters, leaving their semantics entirely ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves HTML source, either from the page or a specific frame, using a specific verb and resource. However, it doesn't differentiate from siblings like ie_text or ie_get, which could cause confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives (e.g., ie_text for text, ie_screenshot for images). The description only implies usage for HTML source but lacks exclusions.

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

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

No annotations provided, so the description carries the full burden. It mentions execution context (page or frame) and return of result, but does not disclose potential side effects, execution timeout, security implications, or whether it modifies page state.

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

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

A single, concise sentence that efficiently conveys the core purpose. No redundant words, but could be better structured to include more detail without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 3 undocumented parameters, no annotations, and no output schema, the description is too minimal. It does not explain return value format, error handling, or prerequisites, leaving an AI agent with insufficient information to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so description must explain parameters. It mentions 'script' implicitly and 'frame' generally, but does not explain the 'limit' parameter or how to specify a frame (string vs integer). The description adds minimal meaning beyond the schema structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'execute', the resource 'JavaScript in the page or a frame', and the outcome 'return the result'. This distinguishes it from sibling tools that navigate, click, or extract text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives like ie_click or ie_fill. The description only states what it does, not when it's appropriate.

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

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

The description discloses the scope: only recorded processes for crashed sessions, never live agents or unknown. With no annotations, this fulfills the burden well, though it could mention any potential side effects (e.g., whether it prompts or logs). Still highly transparent.

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

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

Two sentences, no waste. The first sentence states the action, the second adds critical restrictions. Perfectly front-loaded and concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters, no output schema, and no annotations, the description fully covers what an agent needs: purpose, scope, and constraints. It is complete for tool selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, and schema coverage is 100% (vacuously). The description adds meaning beyond the schema by explaining the tool's behavior without needing parameters. Baseline for 0 params is 4, and the description meets that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool terminates IE-mode Edge / IEDriver processes for crashed sessions, distinguishing it from killing live agents or unknown processes. It uses a specific verb (terminate) and resource (orphan processes), and the exclusion of live agents differentiates it from sibling tools like ie_close.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description explicitly states when to use (crashed ie-mcp sessions) and when not to use (live agents, unknown processes). This provides clear guidance for agent decision-making, effectively differentiating from alternatives among sibling tools.

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

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

Without annotations, the description carries the transparency burden. It mentions session reuse and keeping alive but omits details like what happens on failure, concurrency, or permissions. Adequate but not exhaustive.

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

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

Two sentences efficiently convey core purpose and behavior. Could be slightly more structured but is appropriately sized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should explain return values or status. It only mentions session persistence. With many sibling tools, it could better contextualize its role. Adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with basic descriptions. However, the description contradicts the schema: description states default URL is 'IE_DEFAULT_URL', while the schema says 'about:blank'. This inconsistency undermines clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool starts or reuses an Edge IE-mode session and navigates to a URL, distinguishing it from siblings like ie_goto which likely navigate without session management. However, it does not explicitly contrast with similar tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies this tool is for initial session setup and reuse, but lacks explicit guidance on when to use alternatives like ie_goto for navigation within an existing session. No exclusions or prerequisites are mentioned.

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

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

With no annotations, the description carries the burden. It covers basic behavior: key names and element targeting. However, it does not disclose behavior for parameters like 'wait', 'frame', or 'by'/'value' selectors. The tool's side effects (e.g., triggering events) are implied but not stated.

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

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

The description is a single sentence followed by key name examples. Every word is necessary, and the structure is efficient. No fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters and no schema descriptions, the description is only partially complete. It explains the core function and key naming but omits details on element targeting, waiting, and frame handling. For a 'press key' tool, it is adequate for basic use but lacks full coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%. The description only explains the 'key' parameter by listing valid key names. It fails to explain 'by', 'value', 'wait', and 'frame', which are critical for correct usage. This leaves the agent guessing about element targeting and timing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Press a key on an element' and distinguishes between targeting a specific element (if by/value given) or the active element. It also lists valid key names, making the tool's purpose explicit. This differentiates it from sibling tools like ie_click or ie_fill.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage scenarios: when you need to press a key on an element or the active element. It does not explicitly state when not to use it or name alternatives, but the context is clear enough for an AI agent to infer appropriate use cases.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It only states the action (resize) but does not mention side effects, whether the page state persists, or any other behavioral traits.

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

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

The description is a single sentence, front-loaded, and efficient. It earns its place by adding a practical use case (screenshots). However, it could be slightly more structured with parameter hints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 integer params, no output schema), the description is minimally adequate. It conveys the primary function but lacks parameter semantics and usage boundaries, making it only moderately complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. However, it does not provide any meaning beyond the parameter names (width/height), such as units or constraints. This leaves the agent guessing about expected values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Resize the browser window' with a specific verb and resource. The parenthetical '(useful for consistent screenshots)' adds context that helps distinguish from sibling navigation tools like 'ie_open' or 'ie_goto'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention when not to use it. It only implies use for screenshots, but lacks clear usage context.

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

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

No annotations are provided, so the description must fully disclose behavior. It covers output as an image, PNG format, and optional save, but lacks details on error handling (e.g., missing element), prerequisites (visible window), and side effects. This leaves gaps for an agent to anticipate behavior.

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

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

Single, well-structured sentence that front-loads the main action and linearly adds optional details. No wasted words; every phrase adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description should provide more context about return behavior, error states, and parameter interactions. It mentions two modes but omits details on when one might fail or what happens with missing elements. Parameter 'frame' is left unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Description clarifies that by/value are used for element screenshots and save_path for optional saving, but fails to explain the 'frame' parameter (no schema description) and 'no_inline' (schema description exists). With 60% schema coverage, description adds moderate value but misses critical parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: capturing a PNG screenshot of the IE-mode window or a single element using by/value. It distinguishes itself from sibling tools (no other screenshot tool present) and provides specific details on output format and optional saving.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description explains two usage modes (full window vs. element screenshot) and optional save_path, but does not explicitly state when to use which mode or provide exclusions. Sibling tools offer no alternative screenshot functionality, so the tool is effectively unique.

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

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

No annotations exist, so description must carry the burden. It discloses basic behaviors (scroll types) but lacks details on side effects, error handling, or required permissions. Adequate but not thorough.

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

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

Two sentences, front-loaded with modes and a use case. No superfluous text; every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 6 parameters and no output schema or annotations, the description covers the main modes but does not explain parameter interactions, defaults, or constraints (e.g., can 'by' and 'to' be combined?). Adequate but incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds meaning beyond the sparse schema descriptions: maps 'by/value' to bringing element into view, 'to' to scroll positions, 'dx/dy' to pixel scroll. Only 'frame' is not explained, but overall adds significant value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb (scroll) and resource (element or page/container), with specific modes: bring into view, scroll to top/bottom, or by pixels. Distinguishes itself from sibling tools like 'ie_click' or 'ie_fill'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Provides a clear use case: 'Needed for virtualized grids.' Implies when to use but does not explicitly state when not to use or list alternatives.

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

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

No annotations provided. Description only states how to identify the option but does not disclose what happens after selection, error conditions, or side effects. It implies mutation of the dropdown selection but is not explicit.

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

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

Single sentence of 15 words, no fluff. All information is front-loaded and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 6 parameters and no output schema or annotations, the description is too sparse. It does not explain the return behavior, failure cases, or the role of all parameters. Additional context is needed for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 50% coverage with descriptions for index, label, and option_value. The description adds context that these are the selection methods, but it fails to explain the 'by' and 'value' parameters which are in the schema. The description partially compensates but introduces ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states selecting an option in a select dropdown via label, option_value, or index. However, the requirement to provide exactly one conflicts with the schema having two required parameters (by and value), causing slight confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool compared to sibling tools like ie_click or ie_fill. The description says to provide exactly one of the identifiers, but the schema requires both 'by' and 'value', which is contradictory.

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

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

No annotations exist, but the description accurately describes the simple blocking sleep behavior. Could mention potential effects on automation flow, but given the trivial action, it's largely sufficient.

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

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

Extremely concise with a single meaningful sentence plus parenthetical guidance. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a simple sleep tool with no output schema. The brief description covers purpose, usage, and alternatives.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter 'seconds' is explained by 'sleep for N seconds', compensating for the schema's lack of description. No further details needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool sleeps for N seconds and distinguishes itself from siblings by suggesting ie_wait_ready/ie_wait_text as preferred alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Explicitly marks itself as a last resort and names two preferable alternatives, providing clear when-to-use guidance.

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

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

No annotations are provided, so the description must cover behavioral traits. It describes the output but does not mention side effects, safety (read-only nature), rate limits, or whether the tool modifies session state. For a read operation, 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.

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

Single sentence packed with key information. It is concise and front-loaded, though a list format could improve readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and no output schema, the description covers the main return fields. It is reasonably complete for a status tool, though some details (e.g., exact structure of JSON) are implied rather than explicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so the description's role is minimal. It effectively describes the output structure, which adds value beyond the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states it returns session state as JSON, listing specific fields (active/alive, title, url, window_handles, interaction mode, etc.). This clearly distinguishes it from sibling action-oriented tools like ie_click or ie_fill.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies use as a status/check tool but does not explicitly state when to use it versus alternatives. No guidance on when not to use or what prerequisites exist.

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

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

Without annotations, the description is the sole source of behavioral info. It fails to mention side effects, permissions, or any limitations (e.g., whether text is extracted from the DOM after rendering, or if the tool waits for page load).

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

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

The description is extremely concise, consisting of a single sentence. While this is efficient, it omits important details that could be structured for clarity, such as parameter explanations or return type.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description does not explain the return value format, behavior when no text is found, or how the 'limit' parameter affects output. This leaves the agent with insufficient information to confidently use the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers only 50% of parameters (frame has a brief description, limit has none). The description does not add any additional meaning beyond the schema, leaving the 'limit' parameter completely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool retrieves visible text from a page or a specific frame, distinguishing it from sibling tools like ie_html (HTML) and ie_screenshot (visual). However, it could be more specific about what 'visible text' entails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is given on when to use this tool versus alternatives (e.g., ie_html for full source, or ie_get for attribute). There is no discussion of preconditions or expected outcomes.

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

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

With no annotations, the description should fully disclose behavior. It mentions 'sending a local file path' but does not explain whether this triggers a file selection dialog or directly sets the input value, nor does it state side effects or requirements (e.g., file existence). The behavior remains ambiguous.

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

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

The description is a single short sentence, which is concise but lacks essential detail. It could be expanded to cover parameters and usage context without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 4 parameters (3 required) and no output schema, the description is insufficient. It fails to explain how to specify the file input element (by/value/frame) and what the tool does beyond setting a path. The definition is incomplete for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 4 parameters with only 25% description coverage (only 'path' is described). The tool description adds no additional meaning for the parameters 'by', 'value', or 'frame', leaving them unexplained. This is a critical gap for a required parameter (by, value, path).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's purpose: setting a file input by providing a local file path. It effectively distinguishes from sibling tools like 'ie_fill' (for text inputs) and 'ie_click' (for actions). The verb 'set' is specific and the resource is well-defined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage for file upload scenarios, but lacks explicit guidance on when to use versus alternatives like 'ie_fill' or prerequisites (e.g., the file input must exist and be visible). No when-not or alternative tool suggestions are provided.

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

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

No annotations exist, so description carries full burden. It discloses the wait-for-appearance/disappearance behavior. However, it omits what happens on timeout or errors, and doesn't mention polling mechanics 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.

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

Two concise sentences, front-loaded with the core purpose. No wasted words, efficient for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters, no output schema, and no annotations, the description should provide more behavioral context (e.g., default timeout behavior, success/failure signals). It covers the basic wait logic but lacks completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (only 'gone' and 'timeout' have descriptions). The description echoes 'gone=true' but adds no new meaning for 'by', 'value', 'frame', or 'interval'. With low coverage, it should compensate more.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (wait for an element) and specifies two modes: appear or disappear. It distinguishes from siblings like ie_wait_text by focusing on element selectors rather than text patterns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Explicitly advises to use 'before acting on slow-rendering content', providing a clear context. Lacks explicit when-not-to-use or alternatives, but the guidance is direct and actionable.

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

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

No annotations provided, so description carries full burden. It explains the waiting conditions (readyState + DOM settled), handling of async content, and return values. Slightly lacking detail on side effects or prerequisites, but sufficient for a wait tool.

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

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

The description is concise, front-loaded with purpose, then usage guidance, then return info. Every sentence provides value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description includes return value details (loaded, frame count, etc.), which is good. Could mention edge cases like timeouts, but overall complete for a wait tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions. The tool description does not add 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.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool waits for page readiness (document.readyState complete and DOM settled). It specifies the exact conditions and distinguishes from waiting for specific values, which avoids confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Explicit guidance: 'Use THIS to know content is ready, then search the data separately' and 'Do NOT wait for a specific value to detect load'. This helps the agent decide when to use this tool versus other approaches.

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

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

No annotations are provided, so the description carries full burden. It explains polling behavior, frame scanning, and the return of a match preview. It could mention default timeout/interval values explicitly, but overall good disclosure.

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

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

Two sentences with clear, front-loaded information. No unnecessary words, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity and lack of output schema, the description adequately explains the polling behavior and return info. It could be more specific about the preview format or return structure, but it's sufficient for a wait tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%. The description adds meaning to 'contains' (substring), 'gone' (disappear), and 'frame' (all frames unless given). However, it does not describe 'case_insensitive' or give explicit defaults for 'timeout' and 'interval', which the schema partially covers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool polls until a substring appears (or disappears with 'gone'), scanning all frames unless a specific frame is given, and returns which frame matched plus a preview. It distinguishes itself from ie_wait_ready for page load detection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Explicitly states when to use (for slow async content) and when not to use (for page load, use ie_wait_ready). Also mentions the 'gone' option for disappearance and frame targeting.

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