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

With no annotations, the description carries the behavioral burden. It clearly indicates a read-only account lookup by using 'Show' and lists returned content, but it does not explicitly mention absence of side effects, authentication requirements, or what happens if no account is connected.

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: the first states exactly what the tool does, and the second gives the practical use case. Every word earns its place with no redundancy or filler.

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

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

For a simple parameterless account lookup, the description is nearly complete: it names the resource, the returned fields, and the scenarios in which to use it. It lacks only minor detail about the output format or failure behavior, which is not critical for this 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?

There are zero parameters, so there is nothing for the schema to document. The description adds value by explaining what information the tool retrieves, matching the baseline for a parameterless tool.

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 ('Show') and names the exact resource ('the Phyll account connected on this computer') and the specific data returned (email, plan, free reviews left). It is immediately clear what this tool does and is distinguishable from siblings like upgrade or start_review.

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 the tool: 'Use it when a review is refused or the person asks about their plan.' This gives clear triggering contexts, though it does not explicitly name alternatives or state when not to use it.

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 explicitly states that the tool navigates back one page and reports the resulting browser location, which is helpful. However, it does not mention edge cases like an empty history or potential side effects (e.g., losing form input), leaving some behavioral ambiguity.

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

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

The description is a single sentence that is front-loaded with the action, uses the analogy efficiently, and contains no filler words. Every part contributes to understanding the tool's 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 zero-parameter tool, the description covers the core action and the reporting behavior. It lacks details about the output format and error conditions, but these are minor for such a simple tool and the description is sufficient for an agent to call it correctly.

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

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

With zero parameters and an empty schema, the description does not need to add parameter meaning. The baseline of 4 applies because there are no parameters to explain, and the description adds no unnecessary parameter-related content.

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 ('go back') and resource ('browser's history'), and the analogy to the back button makes the purpose unambiguous. It is clearly distinguishable from siblings like 'open' or 'probe', which are different navigation 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 'like the back button' provides clear context for when this tool is appropriate: when the agent needs to emulate a standard browser back action. It does not list exclusions or alternatives, but the simplicity and sibling set make the intended use obvious.

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

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

With no annotations, the description carries the full burden and does so well: it discloses side effects (files saved in the report folder), constraints (only the app's own origin, max 12 routes), and return information (files saved, HTTP status, JS errors). This goes well beyond a basic statement of what the tool does.

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

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

Three dense sentences, each earning its place: the operation, the workflow timing, and the return value/constraints. No filler or repetition of schema content.

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

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

The description explains inputs (with schema covering defaults), behavior, side effects, constraints, and return values despite no output schema. An agent has everything needed to invoke it correctly at the right point in the review 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 description coverage is 100%, so the schema already fully documents the routes parameter, including examples and default behavior. The tool description adds no parameter-level meaning beyond that, which matches the baseline for high 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 action ('Save a screenshot and the probe results of each route') with a clear resource (routes) and concrete detail (two viewport sizes, report folder). This distinguishes capture from sibling tools like screenshot or probe by framing it as a composite operation, so an agent can identify when this tool is the right one.

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

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

It gives explicit timing: 'Use it right after start_review, before walking the core jobs.' It does not name alternatives or state when not to use it, but the workflow placement is clear enough to guide selection.

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

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

With no annotations provided, the description carries the behavioral burden. It discloses the hidden-input fallback behavior ('clicks the visible text instead, like a person would') and states that the tool returns the new state and subsequent side effects. This goes meaningfully beyond a bare description.

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

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

Three sentences, each earning its place: the core operation, the hidden-input behavior, and the return value. The most important scoping information is front-loaded, with no filler or repetition.

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

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

For a low-complexity tool with two parameters and no output schema, the description covers how matching works, what interaction occurs, and what is returned. The phrase 'anything that followed' is slightly vague, and failure/not-found behavior is omitted, but these are minor gaps.

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

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

Schema description coverage is 100%, so the baseline is 3. The description reinforces that matching is by visible label, but it does not add substantive detail about the parameters beyond what the schema already documents.

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 ('check or uncheck') with a specific resource ('checkbox or radio button found by its label'), and distinguishes itself from generic interaction by noting how hidden inputs are handled. This clearly separates it from siblings like click, fill, and select.

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

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

The description implies the right context: use this when the target is a checkbox or radio button identified by visible label. However, it never explicitly says when not to use it or names alternatives like click or select, so the routing guidance is only implicit.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals fallback matching, return contents ('what was clicked, how many elements matched, and any dialogs, new tabs or JavaScript errors'), and the browser going back after cross-site navigation. This is unusually transparent, though it does not mention all possible side effects like form submission or state changes.

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

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

The description is compact and well-structured. Every sentence earns its place: core action, targeting strategy, fallback behavior, return information, and navigation side effect. There is no redundant or filler content.

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 five optional parameters, no output schema, and no annotations, the description covers targeting, fallback, return values, and navigation side effects. It could go further on when to use this versus sibling tools or what happens during page load, but the essential calling context is present.

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

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

The input schema already documents all five parameters in detail, so the baseline is 3. The description adds meaningful semantics beyond the schema by explaining the role+name pairing, the visible-text fallback, and what happens when no role/name match occurs, which helps an agent use the parameters correctly.

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 action and resource clearly: 'Click an element the way a person would.' It also specifies targeting strategies via role/accessible name or visible text, which is specific enough to understand what the tool does. It does not explicitly compare itself to siblings like press, check, or select, but the element-focused wording is distinct.

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 intended use is implied: click an element by role/name or visible text, with a fallback when role/name fails. However, there is no explicit guidance about when to prefer this tool over siblings like check, select, or press, nor are there exclusions or when-not-to-use conditions.

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 fully carries the burden. It discloses the replacement behavior, the label/placeholder matching fallback, the return value, and includes a strong safety warning about test data. This exceeds the minimal expectations for a mutation tool without annotations.

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 sentences with zero waste. The main action is front-loaded, and each sentence adds critical information: behavior, field-finding logic, and data safety. Perfectly sized for the tool's complexity.

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

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

Given a simple 3-parameter tool with no output schema or annotations, the description covers all necessary aspects: how to identify the target, the overwriting behavior, return information, and safe usage guidance. An agent can invoke this tool correctly without any further clarification.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics by explaining the precedence and fallback between label and placeholder, which is not fully captured in the schema's individual parameter descriptions.

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 ('Type') and resource ('text field') with the key behavior of replacing existing content. Clearly distinguishes itself from siblings like click, select, and check, which perform other actions on form elements.

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

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

Provides clear context on how to use the tool, including field location by label or placeholder and the fallback order. It does not explicitly name alternatives or exclusion conditions, but the description implies it is for text inputs, which is sufficient given the sibling set.

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

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

With no annotations, the description carries the full burden and does well: it discloses side effects (sends, checks, scores, keeps, writes report.md), the retry behavior, and the return values (AI tell index and link). It could add more about failure modes, but it is already substantive.

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 bit sentence-heavy but every sentence adds operational value: what to send, when to call, how to handle problems, and what is returned. It is slightly dense but well organized and front-loaded with the core 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 zero-parameter tool with no output schema, the description covers the full workflow: input file, destination, expected processing, retry guidance, and return values. Nothing essential is missing for an agent to invoke it correctly.

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

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

The tool has zero parameters, so the baseline is 4. The description correctly avoids inventing parameter details and instead explains the data flow, which is more relevant here.

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

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

The description clearly states the specific action: sending report.json to Phyll's engine, which checks, scores, keeps it with a link, and writes report.md. It also distinguishes this from the workflow by explicitly saying 'Call it last,' which separates it from siblings like start_review.

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 explicit usage context: 'Call it last' and describes the retry loop when the engine returns a list of problems. It does not name alternatives or exclusions, but for a zero-parameter finalization tool, the guidance is clear and sufficient.

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

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

With no annotations, the description carries the full behavioral burden. It discloses the dependency on an active review and states the return value is the guide's text, but it does not clarify side effects (though 'get' implies read-only), error behavior, or what happens if the prerequisite is not met. This is adequate but not rich.

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

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

Two focused sentences with no wasted words. The core operation is stated first, followed by the prerequisite and return value. Every sentence earns its place.

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

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

For a simple read-style tool with full schema coverage, the description covers the key context: when to call it, what it needs, and what it returns. It does not explain error cases or the exact meaning of 'the method received', but it is sufficient for an agent to use the tool successfully in the described flow.

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 parameter descriptions already explain each enum value and the tells behavior, including the no-ids fallback. The tool description adds no new parameter-level semantics beyond the schema, so the baseline score of 3 is appropriate.

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

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

The description clearly states the action ('Get one part of Phyll's review method...') and the resource (guide text from the review engine), distinguishing it from sibling tools that perform scanning or capture actions. The phrases 'from its engine' and 'when the method you received points to it' are somewhat jargon-heavy but do not obscure the core purpose.

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

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

The description gives a clear usage condition ('when the method you received points to it') and an explicit prerequisite ('Needs a review started with start_review'). It does not enumerate when not to use the tool or name alternatives, but the prerequisite provides enough context for correct invocation.

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

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

With no annotations provided, the description carries the full burden. It discloses that the tool waits for page load, returns HTTP status on error, and reports dialogs, blocked requests, and JavaScript errors. However, it does not clarify side effects on current review state, session, or previous navigation history.

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 tight and front-loaded: action, wait behavior, usage intent, return value, and a clear safety constraint. Every sentence earns its place with no redundant phrasing.

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 single-parameter navigation tool with a fully documented schemaable path, the description is complete. It even explains return values despite the lack of an output schema, covers error handling, and states the external-site restriction.

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

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

The schema already fully describes the single path parameter with examples and the origin constraint. The description adds no new parameter-level meaning beyond what the schema provides, so 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?

The description states a specific action ('Open a page of the app in the review browser') and a concrete resource ('page of the app'), with a clear wait-for-load behavior. It also distinguishes this tool from siblings like capture, screenshot, and start_review by explaining it begins a walk or returns to a known screen.

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 when to use it: 'begin a walk on a given screen or to return to a known one.' It also states a constraint ('Pages on other sites are refused'), but it does not explicitly contrast with alternative navigation tools like back or 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?

With no annotations provided, the description carries the full burden. It discloses that the tool physically presses a key, may trigger side effects like form submission or dialog dismissal, and then reports the focused element. This gives a meaningful behavioral picture beyond the raw schema.

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

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

Two sentences with no filler: the first states the action and result, the second lists practical use cases. Everything earns its place and the most important information is front-loaded.

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

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

The description covers the action, the outcome, and common usage scenarios. It does not explain edge cases such as navigation or page changes after the key press, but for a simple keyboard tool with a fully documented single parameter, the provided context is largely 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 100%, with the 'key' parameter already described as a Playwright key name with examples. The description does not add new parameter-level detail, so the baseline of 3 is appropriate.

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

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

The description states a specific verb ('press a key'), a specific resource ('the current page'), and a clear observable outcome ('report which element holds the focus afterwards'). This clearly distinguishes it from sibling tools like click, fill, select, and check.

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 gives three concrete use cases: testing keyboard access, submitting a form with Enter, and closing a dialog with Escape. It does not explicitly state when not to use it or name alternative tools, but the context is clear enough for an agent to select it appropriately.

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 discloses that it saves numbers as JSON to a report folder and returns a short summary, which are behavioral traits. It does not mention side effects or permissions, but it clearly indicates it produces a file and a summary.

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 the main action and metrics, followed by return behavior and usage. No wasted words.

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

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

For a single-parameter tool with no output schema and no annotations, the description covers the main aspects: what it does, what it returns, and when to use. It could detail the summary format but that's minor.

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

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

The schema already describes the 'name' parameter with its role in file naming. The description adds no further meaning beyond the schema, so with 100% coverage, 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?

The description states a specific verb 'Measure' and resource 'current page', and enumerates exact metrics (contrast, button size/position, icon buttons without names, dead links, unlabeled form fields, decoration). This clearly distinguishes it from siblings like screenshot or capture, which focus on visual capture rather than quantitative measurement.

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

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

It explicitly says 'Use it on each screen you judge', providing a clear context for when to invoke the tool. It does not name alternatives or exclusions, but the instruction is sufficient for an agent to know this is the measurement tool for evaluation.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently warns that the current page will be loaded again and that anything kept only in memory is reset, which is important side-effect context for an agent deciding whether to invoke 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?

Two sentences with no filler. The primary action is front-loaded, and the behavioral warning follows immediately. Every sentence earns its place.

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

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

For a single-parameter tool with no output schema, this description is complete: it states what the tool does, when to use it, and what side effects occur. An agent can correctly select and invoke it without additional context.

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

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

Schema description coverage is 100%, and the parameter enum already documents the exact sizes (1440 by 900, 390 by 844 with touch). The description adds little beyond calling them 'laptop size' and 'phone size', so it does not need to compensate for schema gaps.

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 a specific action ('Switch the review browser between laptop size and phone size') and a specific resource ('review browser'). It also differentiates from sibling tools like open, click, and back by focusing solely on viewport resizing, with an explicit teleological note about checking phone screens.

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

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

It provides clear contextual guidance: use this tool to check how a screen works on a phone. It does not explicitly name alternatives or say when not to use it, so it stops short of full exclusionary 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?

With no annotations, the description carries the behavioral burden and does well: it discloses that no account is needed, no AI is involved, and the result is a static index. It does not explicitly state read-only behavior, but 'scan' strongly implies it.

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 concise sentences: what it scans, what it returns, and when to use it. There is no filler, and the core purpose is front-loaded.

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

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

Despite having no output schema, the description enumerates the return values clearly, including the index range and meaning. With only one well-documented parameter and clear usage context, nothing essential is missing.

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

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

The only parameter, dir, has a complete schema description covering default behavior and relative path handling. The tool description adds no extra parameter meaning, so the baseline score of 3 is appropriate.

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

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

The description states a specific verb, resource, and goal: 'Scan a project's source code for AI tells'. It also clarifies the output (index, file/line details) and distinguishes itself from start_review, making its purpose 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?

The description explicitly says start_review already runs scan and positions scan as a quick check outside a review. This gives clear when-to-use guidance and names the alternative, so an agent can route correctly.

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

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

With no annotations, the description carries the behavioral disclosure burden. It reveals the file destination, the file naming convention, and the fact that the image is returned for inspection. The full page vs. visible window behavior is documented in the schema, adding further transparency.

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

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

The description is compact and front-loaded with the core action, followed by a precise usage instruction and a file naming note. Every sentence earns its place with no filler.

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

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

For a simple two-parameter tool with a complete input schemahare, the description plus schema covers what is saved, where, how to name it, and what is returned. It is slightly incomplete only in not distinguishing itself from the similar sibling tools capture and snapshot.

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 already documented well. The description adds the file naming pattern 'screens/<size>-<name>.png', which slightly enriches the name parameter, but does not meaningfully compensate beyond the schema baseline.

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 and resource: save a screenshot of the current page into the report folder as evidence, and return the image. However, it does not differentiate itself from the sibling tools capture or snapshot, so it stops short of a 5.

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: 'Take one for each moment a finding refers to.' This is a clear context for when the tool should be used, though it does not mention when not to use it or name alternatives such as capture or snapshot.

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 does disclose that the tool 'Returns the choice made and anything that followed,' which is useful post-action information. However, it does not describe potential side effects such as navigation, form submission, or page changes that selecting an option might trigger.

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

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

The description is two concise sentences with no filler. The core action and locator strategy are front-loaded, and the return behavior is stated succinctly. Every sentence earns its place.

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

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

For a simple two-parameter tool with fully documented parameters and no output schema, the description covers purpose, locator method, and return value. It lacks explicit side-effect disclosure, but given the low complexity, the description is largely complete for an agent to call 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 100%, so both parameters are already well documented in the schema. The description adds only marginal semantic value by reiterating that the element is 'found by its label,' which maps to the label parameter. Baseline 3 is appropriate.

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

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

The description uses a specific verb and resource: 'Choose an option in a dropdown list, a select element.' It also specifies how the element is found ('by its label'), which clearly distinguishes this tool from siblings like click or fill. The purpose is immediately understandable.

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 context is clear: this tool is for selecting an option within a dropdown or select element. It does not explicitly name sibling alternatives or state when not to use it, but the resource type makes the intended use apparent. This aligns with 'clear context, 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 full responsibility. It clarifies that the tool is read-only ('Read'), discloses the truncation limit (about 12,000 characters), and explains the marker-line output structure. It does not mention permissions or side effects, but 'Read' already implies non-mutation, and the truncation is a significant behavioral 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?

The description is three sentences with zero wasted words. It front-loads the core action and content, then gives usage timing, then discloses output markers and truncation. Every sentence adds essential information.

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

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

For a tool with no parameters and no output schema, the description covers what it does, when to use it, and important behavioral constraints (truncation, marker lines). It is complete enough for an agent to invoke correctly, though it could theoretically detail how to parse the output further, but the marker-line note covers the key ambiguity.

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, which makes parameter semantics non-applicable. Per the rubric, this case receives the baseline of 4 because there is nothing left undocumented.

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-resource pair ('Read the current page as an accessibility tree') and enumerates the content types (headings, text, links, buttons, fields with roles and names). This makes it distinct from siblings like screenshot (visual) or scan, though it does not explicitly name an alternative.

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

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

The description explicitly advises taking a snapshot 'before clicking or filling' to learn the exact role and name to use. This provides clear context for when to use the tool, but it does not mention when not to use it or point to sibling 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 provided, the description carries the full responsibility for behavioral disclosure. It reveals side effects (creates the report folder), prerequisites (app running, account login), resource consumption (uses one account review), and what it returns (step-by-step method). This is transparent for a review-starting operation.

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

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

The description is three sentences with no filler: it states the action, when to invoke it, what it does, the prerequisite, and the account requirement. The most important information is front-loaded in the first sentence.

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 and no annotations, the description makes the tool safe to invoke: an agent knows when to call it, what inputs are expected through the schema, what side effects occur, what is returned, and what external requirements must be met. Nothing essential is missing for a correct first call.

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

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

Schema description coverage is 100%, so the schema already documents all six parameters well. The description adds no parameter-specific meaning beyond the schema, which matches the baseline expectation of 3.

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

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

The description opens with a specific verb-plus-resource phrase, 'Start a Phyll review of an app that is already running,' and explains what happens: scans source, creates report folder, and returns the step-by-step method. It is easily distinguishable from siblings like finish_review and guide because it is explicitly framed as the first call in the flow.

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

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

It gives direct usage guidance: call it first, once, when the person asks to review, audit, or improve UX. It also states prerequisites (app running, Phyll account logged in). It does not explicitly contrast this with siblings such as guide or scan, but the trigger conditions and sequencing are clear enough.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool returns a link and instructs the agent to give it to the person without opening it or paying. This discloses the expected agent action, but it does not explicitly mention any side effects (e.g., whether a Stripe session is created) or the nature of the link (one-time vs. recurring). Given the simplicity of the tool, this is a solid level of transparency.

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, well-structured sentence that front-loads the primary action ('Get a Stripe Checkout link') and includes essential instructions without redundancy. Every phrase earns its place, making it concise and easy to parse.

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 zero-parameter tool with a clear output (the link), the description fully covers what an agent needs: the purpose, what to do with the result, and a key condition (no limit on reviews). There is no missing information that would prevent correct invocation or handling.

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 the schema coverage is 100% (since there are none). The description does not need to explain parameters, but it adds meaningful context by stating that the link is for a subscription with no review limit. With no parameters to describe, the baseline of 4 is appropriate, and the description does not leave any gaps.

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 action ('Get a Stripe Checkout link') and its resource (subscription to Phyll Pro), and it differentiates the tool by specifying the upgrade purpose. It is specific and unambiguous, leaving no doubt about what the tool does.

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 instructions for how to use the output: 'Give the link to the person; never open it or pay on their behalf.' This clearly defines when to use the tool (when a user wants to subscribe) and what not to do, making the usage context and boundaries explicit.

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