Browser Control MCP by Nova (CIVAI)

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

Since no annotations are provided, the description must carry the behavioral weight. It adds specific context regarding failure handling by explaining the purpose of the `notification_message` field, which is a key operational behavior of this 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 definition is extremely concise and well-structured. It front-loads the definition of the tool ('Low-level action batch') and immediately follows with its primary operational constraint concerning contextual IDs.

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

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

Given the complexity of handling JSON action batches and the constraints on context switching, the description is robust. It covers the operational requirement for context (`tab_id`) and failure notification handling. It is complete enough for an agent to understand when and how to use the tool effectively.

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 defines `tab_id` generally, but the description provides semantic refinement by specifying that this context is required when the batch includes specific actions like 'mouse_click', 'scroll', or 'keys'. This clarifies the functional requirement of the parameter based on tool logic.

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 as a 'Low-level action batch' handler, indicating it performs complex, serialized tasks. It establishes a strong relationship with the specialized sibling tools by implying that sequences of operations are intended here rather than for individual steps.

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 existence of numerous specific sibling tools suggests that this tool should only be used for executing heterogeneous, multi-step action sequences rather than simple individual operations. The description hints at this necessity by focusing on batch execution but does not explicitly contrast it with the simpler siblings.

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

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

With no annotations, the description carries the full burden and discloses almost nothing: no mention of scrolling the element into view, waiting for navigation or network idle after the click, permission/session requirements, or failure modes for an invalidated ref. Only the snapshot prerequisite is surfaced.

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?

Very short and front-loaded, but under-specification rather than conciseness: the 'Cursor parity' parenthetical consumes space without informing, while the parts that need words (behavior after click, parameter meanings) are absent.

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?

A four-parameter, two-required mutation-style browser tool with no annotations, no output schema, and 25% schema coverage needs far more than three words. An agent cannot tell what state changes, what happens on a stale ref, or how tab_id and element interact with ref.

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 25% — only notification_message is documented. The description explains 'ref' obliquely as a snapshot reference, but says nothing about tab_id (which browser tab/session to act on) or the optional 'element' parameter, leaving half the surface ambiguous in both schema and prose.

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

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

States a specific verb (Click) and a specific addressing mechanism (by snapshot ref), which usefully distinguishes it from coordinate-based siblings like browser_mouse_click_xy and browser_drag. The parenthetical 'Cursor parity' is opaque jargon that adds nothing, but the core purpose is unambiguous.

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?

'Snapshot first' encodes a genuine prerequisite — the ref must come from a prior browser_snapshot call — which is real routing guidance. However, it never says when to prefer this over browser_mouse_click_xy, browser_interact, or browser_dom_input, nor what to do when the ref is stale.

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 and no output schema, so the description carries the full burden and delivers almost nothing: no mention of whether existing field content is cleared or appended, whether a selector is mandatory, what happens with an invalid chain, or what the tool returns. "(e.g. 2,7,0)" is the only concrete behavioral hint, and it is unexplained.

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 clause with no padding and the fallback framing is front-loaded, which is good. But for a six-parameter browser interaction tool the size is driven by under-specification rather than economy; the one parenthesis spends characters on a bare example instead of explaining the chain.

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?

A six-param, mutation-style browser input tool with no annotations, no output schema, and 17% schema coverage needs substantially more explanation than two fragments. An agent can guess the fallback role but not how to build a valid chain or which parameters are actually required to succeed.

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 17% (only notification_message is documented), and the description covers just the chain format for one of six params. It never clarifies the relationship between method vs input_method, the role of selector, or how tab_id and text are used, leaving four parameters ambiguous in both schema and prose.

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?

"Run dom input method chain" gives a verb and a resource, and the mention of list_input_methods plus "stubborn fields" hints that this is a fallback text-input path. But "dom input method chain" is jargon: the description never says what actually happens (typing text into a field via a sequence of DOM events), so an agent must reverse-engineer intent from the name.

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?

"use after list_input_methods on stubborn fields" is real sequencing guidance: it tells the agent to call the sibling lister first and reserves this tool for cases where normal input fails. It does not name the obvious alternatives (browser_type, browser_fill) it should be tried after, so the routing is implied rather than explicit.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether the drag uses real mouse events, whether it waits for completion, what permissions or tab state are required, or what side effects occur; only the coordinate frame is implied.

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 single sentence is front-loaded and waste-free, but it is under-specified rather than appropriately concise. It does not provide structural cues about required parameters or sequencing.

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 six-parameter browser-action tool with no annotations and no output schema, the description is too thin. It omits tab scoping, the purpose of notification_message, coordinate semantics, and any indication of return or error behavior.

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

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

Schema description coverage is only 17%, and the description adds just the 'viewport coordinates' meaning for the four coordinate parameters. It leaves tab_id and notification_message unexplained and does not clarify coordinate units or origin, so it only partially compensates for the sparse schema.

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

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

The description states a specific verb ('drag') and locational frame ('viewport coordinates'), so the basic action is inferable. However, it does not specify what is being dragged (mouse pointer, element, selection) or how this differs from siblings like browser_mouse_click_xy or browser_interact.

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

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

There is no guidance on when to use this tool versus alternatives such as browser_mouse_click_xy, browser_interact, or browser_dom_input. No prerequisites, exclusions, or contextual triggers 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?

There are no annotations, so the description must carry the behavioral burden: it does disclose the return shape (ok, value, logs, metrics) and the tab dependency, plus the schema notes the 15s default/120s max timeout. It does not disclose that execution is arbitrary and may mutate page state, nor what error conditions look like when ok is false.

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?

Three short sentences with the action front-loaded and the prerequisite and return contract following. The BrowserGPT Quick Task reference is mild name-dropping but earns its place as an implementation-equivalence hint.

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 four-parameter tool with no output schema, the description still names the return fields, the required tab handle, and the execution channel, which is enough to call it correctly. The main omission is the absence of any warning about side effects of arbitrary JS execution.

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

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

Schema description coverage is 100%, so all four parameters are already documented, including tab_id's source and the timeout range. The description only restates the tab_id dependency and adds nothing about the timeout or notification_message semantics; the baseline of 3 applies.

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

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

States a specific verb and resource — 'Run JavaScript on a target tab' — and adds a concrete implementation note (CDP evaluate path, equivalent to BrowserGPT Quick Task exec_js). An agent can readily distinguish it from siblings like browser_click or browser_navigate, though it never explicitly contrasts against them.

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

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

Provides a genuine prerequisite — 'Requires tab_id from browser_tabs' — which tells the agent to obtain a tab first. However, it gives no guidance on when to prefer this over the higher-level interaction tools (browser_click, browser_fill, browser_snapshot) or when arbitrary JS is inappropriate.

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 implies a DOM mutation but says nothing about whether it fires input/change events, whether it clears existing content, whether it fails silently on invalid refs, or how input_method changes behavior — all critical for a write-like 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 single fragment is not concise-but-complete; it is under-specified. There is zero structure, no front-loaded scope statement, and no information beyond four 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?

A five-parameter browser interaction tool with no annotations and no output schema needs substantially more: ref provenance, input_method options, and failure behavior. None of that is present, so an agent cannot call this safely.

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 only 20% schema description coverage across 5 parameters, the description must compensate and does not. It only restates "ref" (already obvious from the schema) and leaves tab_id, value, input_method, and notification_message entirely undefined in both schema and prose.

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?

"Fill field by ref" names a verb and a resource, so the basic intent is recoverable, but it does not distinguish this tool from close siblings like browser_type, browser_dom_input, or browser_interact. An agent cannot tell from the text why it would pick browser_fill over browser_type.

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

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

There is no when-to-use or when-not-to-use guidance, no mention of prerequisites such as needing a snapshot ref first, and no pointer to alternative tools. The agent must infer everything from the sibling list.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It states a read-like operation but does not clarify permissions, error behavior, return format, or what happens if the ref is invalid, leaving significant gaps.

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

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

The description is a single, front-loaded sentence with no wasted words, which is appropriately sized for a simple getter tool.

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

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

Given the lack of annotations, low parameter schema coverage, and no output schema, the description is insufficient. It omits what ref and tab_id mean, what the bounding box contains, and behavioral details needed to invoke 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 description coverage is only 33% (only notification_message is documented). The description mentions 'ref' but does not explain what a ref is, how to obtain it, or what tab_id represents, so it fails to compensate for the low schema coverage.

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

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

The description uses a specific verb ('Get') and resource ('ref bounding box') and adds the scoping condition 'from last snapshot,' which clarifies the state dependency. It does not explicitly distinguish itself from siblings like browser_highlight or browser_screenshot, but the name and verb make its purpose clear.

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

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

There is no explicit guidance on when to use this tool versus alternatives such as browser_highlight or browser_screenshot. The phrase 'from last snapshot' implies a prerequisite but does not state when the tool should be chosen.

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 and does well: it discloses the extension dependency, that HttpOnly cookies are included, that an interactive operator approval gate exists, and that returned values are sensitive. It omits what happens if the operator denies the prompt and whether values come back raw or redacted.

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 compact sentences, front-loaded with the purpose before mechanism, precondition, and safety caution. Dense and largely waste-free, though the 'via BrowserGPT extension: chrome.cookies' fragment packs three ideas into one clause and slightly blurs the read target.

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 7-parameter tool with no annotations and no output schema, the description covers the permission workflow and sensitivity but says nothing about the return shape (does it return cookie values, names, domains, expiration?) or error behavior on denial. Adequate to invoke, insufficient to predict the result.

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

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

Schema description coverage is 100% and the schema already explains tab_id, cookie_domains (with a domain-format example), key filters, and confirmation_message. The description only restates which sources are optional, adding little semantics beyond the structured fields, so the baseline 3 applies.

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

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

States a specific verb ('Read') and resource ('session data for a tab') and enumerates the concrete sources: chrome.cookies including HttpOnly, plus optional localStorage/sessionStorage keys. No sibling tool in the list reads cookies or session storage, so the agent can distinguish it without opening the schema.

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

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

Gives a clear usage context ('session export / porting auth') and an explicit prohibition ('do not paste values into chat'), plus the precondition that the operator must approve the in-tab permission prompt. It does not name an alternative tool or say when not to use it (e.g. prefer browser_exec_js for page-scoped reads), so it stops short of 5.

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

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

No annotations are provided, so the description carries the full behavioral burden, but it only hints at a brief visual outline. It does not state side effects, whether the page scrolls, whether the highlight is transient, what happens with an invalid ref, or what the tool returns.

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 single sentence is short but under-specified rather than concise. It is front-loaded but omits the essential context needed to understand 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?

For a three-parameter browser action tool with no annotations and no output schema, the description is too incomplete. It leaves the meaning of ref, the role of tab_id, and the expected behavior largely 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?

Schema description coverage is only 33%, with notification_message the sole documented parameter. The description mentions 'ref' but does not explain its meaning, and it ignores tab_id entirely, so it fails to compensate for the low schema coverage.

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 'Briefly outline ref on page' is vague and nearly restates the tool name with a synonym ('highlight' → 'outline'). It does not clarify what 'ref' means or how this differs from sibling browser inspection/interaction 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?

There is no guidance on when to use browser_highlight versus alternatives such as browser_snapshot, browser_interact, or browser_click. The agent must infer usage entirely from the name and schema.

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

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

No annotations are provided, so the description bears the full burden of behavioral disclosure. It says nothing about mutation semantics, side effects, permissions, error handling, or return values for what is clearly an interactive/action-performing 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?

Very short and front-loaded, but this is under-specification rather than conciseness. A five-word sentence cannot carry the required meaning for an 8-parameter interaction tool.

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

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

With no annotations, no output schema, 8 parameters at 13% coverage, and an enum-free opaque `op` field, the description is nowhere near complete enough for an agent to call the tool reliably.

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

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

Eight parameters with only 13% schema description coverage, and the description adds zero parameter information. The `op` discriminator, `ref`, `key`, `code`, `text`, and `input_method` are all undocumented in both places, leaving an agent unable to determine valid values or the relationship between fields.

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?

"Interact via snapshot ref" gives a resource hint (snapshot refs) but the verb "interact" is generic and doesn't say what action is performed. Against siblings like browser_click, browser_fill, browser_type, and browser_press_key it's impossible to tell what this generic tool does that they don't.

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

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

No when-to-use guidance, no exclusions, no mention of alternatives. The description offers no basis for choosing this tool over the many specific siblings (browser_click, browser_fill, browser_dom_input).

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

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

No annotations are provided, so the description carries the full behavioral burden, yet it discloses almost nothing: no indication of whether the click waits for navigation, what errors occur on invalid coordinates, or whether tab_id must be an active tab. Only the 'viewport' qualifier adds real context.

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

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

A single front-loaded sentence with no filler and the condition stated immediately. It is efficient, though so terse that it borders on under-specification rather than ideal 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?

For a four-parameter mutation tool with no annotations, no output schema, and low schema coverage, the definition omits too much: tab_id semantics, coordinate origin/units, click side effects, and notification_message usage are all unaddressed.

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 25%, and the description only clarifies that x/y are viewport-relative rather than page-relative. The required tab_id and the optional notification_message behavior are left entirely to the schema, which is thin, so the description does not compensate for the coverage gap.

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

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

States a specific verb and resource ('Click at viewport x/y'), which is clearly distinguishable from the coordinate-free sibling browser_click. It doesn't name browser_click explicitly, but the phrase 'when snapshot refs are empty' implicitly scopes it to the coordinate-fallback case.

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 triggering condition ('when snapshot refs are empty'), which is the key routing signal versus the ref-based browser_click. It stops short of naming the alternative tool or describing what to do if both refs and coordinates are available.

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 at all, the description carries the full burden, and it does disclose one valuable behavioral trait: the return shape ("Returns tab_id in results[0].tab_id"). It leaves out whether navigation blocks until load, what happens on invalid URLs or timeouts, and whether a new tab is created versus the current one being replaced.

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, zero filler, and the core action leads before the tab-handling detail. The return-value note is compressed into a single clause rather than a separate paragraph.

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 three-parameter, annotation-free tool with no output schema, the description covers the tab-selection axis and the return field, which is the main thing an agent needs. It is still thin on failure modes, load behavior, and the user-facing notification_message parameter, so it stops short of fully self-sufficient.

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 67% and url has no schema description, so the description usefully supplies the missing default semantics: omit/empty tab_id means the active control tab, and the resulting tab_id comes back in results[0].tab_id. notification_message is not touched in the description but is adequately explained in the schema.

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

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

States a specific verb + resource ("Navigate a tab to URL") that is unmistakable against the mostly mouse/DOM-oriented siblings like browser_click and browser_fill. It doesn't explicitly contrast with browser_tabs, though it does reference it, so the boundary between navigating and tab management is implied rather than stated.

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

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

The tab-reuse rule ("Pass tab_id from browser_tabs to reuse an existing tab; omit or leave empty to use the active control tab") is genuinely useful selection guidance. However, there is no explicit when-to-use vs. when-not, and no mention of preconditions such as an open control session existing before navigation can succeed.

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

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

No annotations exist, so the description carries the full behavioral burden. It implies a synthetic input action but does not disclose focus requirements, whether the tab must be active, whether modifiers are supported, error behavior for invalid tabs, or any side effects.

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

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

The single sentence is short but under-specified rather than economical. It does not front-load important context such as focus requirements or supported key formats.

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 five-parameter input tool with no annotations, no output schema, and low schema coverage, the description is far too thin. It does not provide enough contextual detail for an agent to invoke the tool correctly in varied browser scenarios.

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 20% and the description does not explain any of the five parameters. Critical parameters like modifiers_json and code are undocumented in both schema and description, and even the required tab_id and key lack usage details.

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

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

The description states a specific verb and resource ("Press keyboard key") scoped to a tab, which is enough to understand the basic action. However, it does not distinguish this from siblings like browser_type or browser_dom_input, so an agent may not know when a single keypress tool is preferred over text entry.

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

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

There is no guidance on when to use this tool versus browser_type, browser_fill, or browser_dom_input, nor any mention of prerequisites such as element focus or active tab state. The agent is left to infer usage entirely.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the JPEG format and viewport scope, but does not explain the return behavior, whether the screenshot is inline data or a reference, or how the required tab_id affects capture.

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

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

The description is a single front-loaded sentence with no wasted words. Its brevity is appropriate structurally, even though it leaves behavioral and usage details sparse.

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 screenshot tool whose parameters are fully documented in the schema, the description gives the essential output format and capture scope. However, without annotations or an output schema, it should say more about what the agent receives back and how the screenshot is delivered.

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

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

Schema description coverage is 100%, so both tab_id and notification_message are already documented in the schema. The description adds no additional parameter meaning, which is acceptable at baseline when the schema does the heavy lifting.

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

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

The description states the specific resource and output format: a JPEG screenshot of the session viewport. It is clear what the tool produces, though it does not explicitly differentiate itself from nearby screenshot- or DOM-inspection siblings such as browser_snapshot.

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

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

There is no guidance on when to use this tool instead of alternatives like browser_snapshot, browser_get_bounding_box, or other browser inspection tools. The viewport scope is implied, but no usage conditions or exclusions 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 are provided, so the description carries the full disclosure burden. It reveals only that ref triggers a scroll-into-view, omitting direction/defaults, what happens when amount and deltaY are both supplied, conflict/priority rules, and whether the call returns anything or requires focus. For a mutation-style interaction tool with zero annotation coverage, this is a substantial 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?

A single short sentence with the core action front-loaded and the optional-ref nuance second; no wasted words. The terseness is a deliberate trade-off rather than padding, though it leaves gaps handled elsewhere in the scoring.

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 six parameters, 17% schema coverage, no annotations, and no output schema, this tool needs considerably more context than one sentence provides. An agent cannot determine how to set amount versus deltaX/deltaY or what result to expect after calling.

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 17%, so the description must compensate and it largely does not: only ref gets any explanation ('scrolls element into view first'). amount, deltaX, deltaY, tab_id, and their interaction (e.g., vertical vs horizontal scrolling, units, defaults) are left completely undocumented in both schema and description.

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

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

The description states a specific verb and mechanism ('Scroll wheel') plus a secondary behavior ('optional ref scrolls element into view first'), so an agent knows exactly what the tool performs. It does not explicitly contrast itself with siblings like browser_press_key or browser_snapshot, but the scroll-wheel framing is distinctive enough to disambiguate.

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

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

There is no guidance on when to reach for this tool rather than alternatives (keyboard paging, snapshot, drag), and no prerequisites or exclusions. The only usage hint is implicit in the words 'scroll wheel'.

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

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

No annotations are provided, so the description carries the full behavioral burden. It implies a browser interaction that changes select state but does not disclose side effects, event triggering, waiting behavior, permissions, or what is returned on success/failure.

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

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

The description is a single front-loaded sentence with no wasted words, but it is under-specified for a four-parameter browser-interaction tool. Conciseness is achieved at the cost of necessary detail.

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

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

With no annotations, no output schema, and low parameter coverage, the description does not provide enough context for reliable invocation. It lacks usage conditions, parameter semantics, and behavioral details that an agent would need.

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 25%; only notification_message is documented in the schema. The description mentions 'select ref' but gives no meaning for values_json (format, multi-select behavior, encoding), tab_id, or ref beyond the word 'select'.

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

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

The description states a specific action (select options) on a specific resource type (a select ref), so an agent can understand the basic operation. It does not, however, distinguish this tool from nearby alternatives like browser_fill or browser_dom_input.

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

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

There is no guidance on when to use this tool instead of browser_fill, browser_dom_input, browser_click, or browser_type. It also omits prerequisites such as whether the ref must point to a <select> element or whether the tab must already exist.

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

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

No annotations are provided, so the description must carry the full behavioral burden. It implies a read-only snapshot but does not disclose side effects, permission requirements, ref lifetime, or what the snapshot actually returns.

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 five-word phrase is concise and front-loaded, but it is under-specified rather than effectively structured. There is no wasted text, yet the brevity leaves key information missing.

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

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

With no annotations and no output schema, the description needs to explain what the snapshot contains and how refs are used. It does not do so, and it also leaves the interactive_only parameter unexplained, making the definition incomplete for a browser snapshot 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 tab_id and notification_message, but interactive_only has no description at all. The tool description does not explain any parameter, and 'with refs' provides no mapping to the inputs.

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 returns an accessibility snapshot with refs, which is somewhat more specific than the tool name alone. However, it does not define what 'refs' are or clearly distinguish the tool from siblings such as browser_screenshot or browser_dom_input.

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

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

There is no guidance on when to use this tool versus alternatives such as browser_screenshot, browser_interact, or browser_actions. The agent must infer usage entirely from the name and the vague phrase 'accessibility snapshot with refs.'

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read-only listing operation and references an open session, but does not explain return format, pagination, permissions, or what happens if no session is open.

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

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

The description is a single front-loaded sentence with no filler. It is efficiently sized, though its terseness leaves little room for useful context.

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 no annotations and no output schema, the description should explain more about the returned data, session requirements, and failure behavior. It provides only the bare scope and leaves significant contextual gaps.

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

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

There is one optional parameter whose schema description coverage is 100%, so the schema already documents notification_message fully. The description adds no parameter-specific meaning, which is adequate given the schema's completeness but not value-adding.

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

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

The description states a specific verb and resource: 'List tabs' scoped to 'the open control session.' This distinguishes it reasonably from sibling list_browsers, though it does not explicitly name that alternative or clarify the relationship.

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 'in the open control session' implies a prerequisite (a control session must be open), but there is no explicit guidance on when to use this versus list_browsers or other browser tools, nor any stated exclusions.

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

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

With no annotations, the description carries the full behavioral burden but discloses almost nothing: it does not say whether existing text is cleared or appended, whether the field is focused first, whether typing is instant or simulated, or what happens on failure. Only the bare mutation ('type') is conveyed.

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 single sentence is front-loaded and wastes no words, but its brevity stems from under-specification rather than disciplined editing. There is no structure to help an agent understand the required ref/tab context.

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

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

For a 6-parameter mutation tool with no annotations and no output schema, this description is far too thin. Critical behavioral choices exposed by 'slowly' and 'input_method' are unexplained, leaving an agent unable to invoke the tool confidently.

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

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

Schema description coverage is only 17%, so the description must compensate, yet it only hints that 'ref' identifies the field. The meaning and effects of 'slowly', 'input_method', and 'tab_id' are left entirely undocumented in both schema and description.

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

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

The description states a specific verb ('Type') and target ('field by ref'), so the basic action is inferable. However, it does not explain what a 'ref' is (presumably from browser_snapshot) nor distinguish this tool from close siblings like browser_fill, browser_dom_input, or browser_interact.

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

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

No guidance is given on when to use this tool versus browser_fill, browser_dom_input, or browser_press_key. There is no mention of prerequisites such as needing a snapshot-derived ref or an active tab.

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

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

No annotations are provided, so the description carries the burden; it does disclose the operational workflow (pre-check with list_browsers, re-check after), which is useful behavioral context. However, it does not say whether the call is idempotent, how long provisioning takes or whether the agent must wait, what happens if a runner already exists, or whether licensing/session setup is required first.

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 compact sentences, front-loaded with the action, then the trigger and follow-up step. Every clause carries operational information; nothing is redundant.

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 lifecycle/provisioning tool with no annotations and no output schema, the definition covers the trigger and the verification step but leaves the agent unsure what 'prepare' entails, how long it takes, and how to recognize success or failure. Adequate to invoke, not adequate to handle the outcome.

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

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

Schema description coverage is 100% and the single optional parameter is fully documented in the schema, so the baseline of 3 applies. The description adds nothing about notification_message, but it doesn't need to.

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?

Names a specific action (start/prepare) and a specific resource (Nova remote BrowserGPT runner), and ties it to the underlying command name so the agent can map it to known behavior. It is clearly distinguishable from the browser_* siblings and from list_browsers, though 'prepare' remains somewhat fuzzy about what actually gets provisioned.

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?

Gives an explicit trigger condition ('when list_browsers shows no online+ready remote node') and the required follow-up ('then list_browsers again'), which is exactly what an agent needs to sequence this tool. No when-not conditions or failure handling are stated, keeping it short of a 5.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not say whether listing requires a valid license, whether it makes network calls to remote nodes (with latency or failure implications), whether results are live or cached, or what the response looks like — and there is no output schema to fall back on.

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

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

One short, front-loaded sentence with the resource first and the scope qualifiers compressed into a parenthetical. Nothing is wasted, though the terseness comes at the cost of the missing behavioral detail noted elsewhere.

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, zero-required-parameter list tool with a fully documented schema, the basics are covered. But with no annotations and no output schema, the description should at minimum state the license prerequisite and roughly what a returned node entry contains; those gaps keep it at minimum-viable.

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 single parameter (notification_message) is fully documented in the schema, so the schema carries the semantics. The description adds nothing about it, which is acceptable at 100% coverage but not a value-add; the baseline of 3 applies.

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

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

States a specific verb+resource ("List BrowserGPT browser nodes") and narrows scope with "local + remote" and "for the configured license." It is clearly a discovery/read operation, cleanly distinguishable from the browser_* action siblings. It stops short of naming any sibling or explaining what a "node" is.

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 the configured license" is an implicit prerequisite hinting that set_browsergpt_license must run first, and the local/remote scope implies it should be called before picking a runner. But there is no explicit when-to-use statement, no exclusion, and no mention of ensure_remote_runner or any alternative for discovering nodes.

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

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

No annotations are provided, so the description carries the full behavioral burden. It implies a read-only listing but does not state permissions, whether the list is global or per-session, what the ids look like, or any rate/scope 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?

A single compact sentence with the core action front-loaded and no filler. It is arguably under-specified rather than verbose, but structurally efficient.

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

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

With no annotations and no output schema, the description should explain what 'input method ids' are and what the response contains, since the schema cannot. It leaves the agent guessing about the return shape and the tool's role in the browser automation workflow.

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

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

Schema coverage is 50%: page_url has no schema description, and the description compensates by explaining it yields a 'domain-specific hint'. notification_message is only documented in the schema itself, so the description adds value for one of two params without fully covering the gap.

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

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

States a specific verb ('List') and resource ('BrowserGPT dom input method ids'), which is clearly distinct from siblings like list_browsers or browser_dom_input. The phrase 'dom input method ids' is somewhat jargon-heavy but specific enough to identify the return type.

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

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

The clause 'optional page_url for domain-specific hint' implies when the parameter is useful, but there is no explicit statement of when to call this tool versus browser_dom_input or other siblings, and no exclusions.

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

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

No annotations are provided, so the description carries the full burden. It does not explain what a control session enables, whether it requires ensure_remote_runner or an existing remote runner, what happens on failure, or what the response contains.

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 zero wasted words, and the key scope (target browser node_id) is front-loaded. There is no unnecessary preamble or repetition.

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

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

For a session-creation tool with no annotations and no output schema, the description is inadequate. It omits prerequisites such as whether a remote runner must exist, what privileges are needed, and what the agent should expect after opening the session.

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 both parameters are already documented. The description adds only "target browser node_id," which repeats the schema, and it does not mention the notification_message parameter at all.

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

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

The description states a specific verb ("Open") and resource ("MCP control session") scoped to a target browser node_id. It is clear what the tool does, but it does not explicitly differentiate itself from siblings like browser_actions or ensure_remote_runner.

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

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

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The only implied context is that target is a node_id from list_browsers, which is already in the schema.

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

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

No annotations exist, so the description carries the full burden. It discloses that this is a persistence/write action gated on auth state, but says nothing about whether repeated calls overwrite an existing license, what errors occur if a license is already set, or whether validation happens on save.

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?

Three compact sentences, with the core save action and the prerequisite condition front-loaded. Wording is slightly awkward ("only if license_not_set") but nothing is redundant.

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 two-parameter setter with a fully documented schema and no output schema, the description covers what to save, where it comes from, when it's needed, and which tool to precede. Missing only overwrite/idempotency and failure semantics.

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

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

Schema description coverage is 100%, so both parameters are self-documenting (license_key as the BrowserGPT key; notification_message as fallback user-facing text). The description adds the origin of the license value but no format, validation, or edge-case detail 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?

States a specific verb and resource ("Save BrowserGPT license") plus the condition under which it's needed (MCP headers didn't supply it). It is clearly distinguishable from siblings like list_browsers, though the jargon ('Nova/SecOps derived license') is opaque without prior context.

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

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

Gives an explicit when-not ("optional when Nova/SecOps derived license from auth") and a precise gating rule ("Call before list_browsers only if license_not_set"), naming the sibling it precedes. It stops short of explaining how an agent detects license_not_set, but the exclusion condition is unambiguous.

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