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

Beyond the annotations (idempotent, not destructive, openWorld), the description discloses that a visible window is opened, the session is persisted under profileDir, and that it returns immediately if already logged in. This adds valuable behavioral context not captured by annotations alone.

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

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

The description is concise with three sentences, each adding essential information. It is front-loaded with the primary action and avoids redundancy or trivial details.

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

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

Given the single parameter and no output schema, the description covers the tool's operation well. It could mention the return behavior (e.g., success/failure indication) but this is not critical. Overall, it is sufficiently complete for an AI agent.

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

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

The schema covers the `waitMs` parameter fully (100% coverage), but the description adds the default value (10 min) which is not in the schema. This extra detail enhances understanding of the parameter's behavior.

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

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

The description clearly states the tool's purpose: opening a visible Chromium window for scanning login on codesign.qq.com. It uses a specific verb ('Open') and resource ('Chromium window'), and distinguishes itself from sibling tools like codesign_logout and codesign_status.

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

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

The description provides clear guidance on when to use the tool: it returns immediately if already logged in, indicating no action needed. However, it does not explicitly mention alternatives or exclusions, such as suggesting codesign_status to check login state first.

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

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

The description discloses the full destructive behavior (closing browser, wiping profile) beyond the destructiveHint and idempotentHint annotations. It also reveals that the result includes the target path for verification.

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, each serving a clear purpose: first states the action, second provides usage instruction and output information. No unnecessary 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?

The tool is simple with one required parameter, no output schema, and obvious destructive effect. The description covers the action, required input, and part of the output. No 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?

The schema already describes the confirm parameter as 'Must be true. Wipes the persistent profile.' The description only repeats 'Pass { confirm: true }' and does not add new semantics about the parameter itself. With 100% schema coverage, baseline 3 is appropriate.

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

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

The description clearly states 'Close any running browser and wipe the persistent profile directory', specifying the action and resource. It distinguishes from siblings like codesign_login or get_artboard_image, which are not destructive.

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 instructs to pass { confirm: true } and suggests verifying the target path before re-running. It does not explicitly compare to sibling tools but the context implies usage when ending a session.

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?

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint. The description adds beyond that by specifying what information is returned (config and status) and that it should be used first. This provides useful behavioral context not covered by 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?

The description is only two sentences. The first sentence states the tool's output, and the second provides usage guidance. No extraneous words; every sentence adds value.

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

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

Given the tool's simplicity (no parameters, no output schema), the description adequately explains what it returns (config and status) and when to use it. It could be slightly more specific about the exact fields in the output, but it is sufficient for an AI agent.

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

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

With zero parameters and 100% schema description coverage, the baseline is high. The description does not need to add parameter info, but it could implicitly state that the tool takes no arguments. However, the empty input schema makes this clear, so no deduction.

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

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

The description clearly states the tool returns MCP server config (profile path, idle settings) and current browser/login status. It uses specific verbs and resources, and distinguishes itself from siblings like codesign_login and codesign_logout by explicitly suggesting use 'first to verify whether the user has logged in.'

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

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

The description explicitly says 'Use this first to verify whether the user has logged in,' providing a clear when-to-use instruction. It implies that other tools are for login/logout, thus giving guidance on 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?

The description goes beyond annotations by specifying that output never includes sensitive values (Cookie, Authorization, password, state-key) or response bodies—only JSON key paths. It also mentions the headless browser side-effect, aligning with the openWorldHint annotation.

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: first describes the core action, second explains use cases and output limitations. No wasted words, key 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 main behavior and output redaction but omits details on the summary format and the effect of parameters like includeHeaders and maxBodyKeyDepth. Given no output schema, more detail would be helpful.

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

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

With 0% schema coverage, the description should explain all five parameters, but it only mentions timeoutMs in context. It does not describe sharingUrl, password, includeHeaders, or maxBodyKeyDepth, leaving the agent to infer their roles.

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

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

The description clearly states the tool opens a sharing page in a headless browser, records network responses for a specified timeout, and returns a redacted summary. This distinguishes it from sibling tools like login, logout, and artboard functions.

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 advises using this tool to discover unknown endpoints or debug tool failures. While it doesn't list when not to use it, the context makes it clear it's for diagnostic purposes rather than routine operations.

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?

Annotations indicate readOnlyHint=false (side effects) and idempotentHint=true. Description adds context: downloading and saving local files under a specific path, which is a side effect but not destructive. It does not contradict annotations and provides additional behavioral insight (e.g., local artifact creation).

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: first states action and source, second provides usage guidance, third describes output and filters. No redundant content; information is front-loaded and 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?

Given 8 parameters and no output schema, the description covers main purpose, usage, output location, and filters. It lacks detail on some parameters (e.g., password, screenId) but is sufficient for an agent to use the tool correctly with contextual understanding from sibling tools.

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 38%, meaning only 3 of 8 parameters have schema descriptions. The description explains layerObjectId, format, and scales, but does not cover sharingUrl, password, screenId, etc. It adds value for key parameters but leaves gaps for others.

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

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

The description clearly states it downloads CoDesign slice assets, specifies the source (official slice manifest), matching method (layer object_id), and output location (local paths). It distinguishes itself from alternatives like Python/PIL or screenshot cropping, making its purpose very 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?

Explicitly says 'Use this for implementation assets instead of using Python/PIL or screenshot cropping,' providing a clear directive on when to use this tool versus alternatives. Also mentions optional filters, further guiding 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?

Discloses that download=true stores the image under a specific path and gives selector precedence, but lacks details on error handling or other behaviors. With no annotations, it carries burden well.

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?

Four sentences, front-loaded purpose, no redundancy, every sentence adds value.

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

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

Covers purpose, guidelines, and key behaviors but omits parameter details, return type, and error scenarios. Adequate but gaps exist.

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

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

Schema coverage is 0%, so description should compensate. It gives selector precedence and mentions download effect, but leaves many parameters (password, sharingUrl format, etc.) unexplained.

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

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

The description clearly states it returns the CoDesign preview/cover image for visual comparison only, and distinguishes from sibling tools by recommending get_artboard_spec and download_slice for implementation.

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

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

Explicitly states when to use (visual comparison) and when not to (do not crop for production slices), and names alternatives (get_artboard_spec, download_slice).

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?

Annotations already provide readOnlyHint, idempotentHint, etc. The description adds behavioral details: handling conflicts between css and fills, selector precedence, default includeSlices, and SCREEN_SELECTOR_REQUIRED response. No contradictions with 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?

The description is moderately long but every sentence serves a purpose: main function, conflict resolution, usage instruction, selector logic, and parameter behavior. Front-loaded with key information, no redundancy.

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

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

Given no output schema and limited parameter descriptions, the description covers essential behavioral aspects, selector logic, and conflict resolution. It mentions return fields (JSON with layers, text, etc.) but could benefit from specifying the output structure more clearly.

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 low (14%), but the description compensates by explaining selector parameters (screenId, objectId, screenName) and their precedence, as well as includeSlices default. It doesn't detail password or layerObjectId, but the overall context is clear.

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

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

Description clearly states it fetches the official meta_url JSON with detailed design elements like layer positions, text, fills, and CSS. It distinguishes itself from siblings by specifying it's the canonical source for design-to-code and warns against using OCR/crop when this tool is available.

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

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

Explicit guidance: 'Use this before writing HTML/CSS from a CoDesign URL.' It advises against cropping/OCR and provides selector precedence. It also explains behavior for multiple screens (returns SCREEN_SELECTOR_REQUIRED). This clearly states when to use the tool and what alternatives to avoid.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. Description adds context about what data is returned and the workflow order, which complements annotations. No contradictions.

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 purpose and usage. Every sentence is valuable and no redundancy. Highly 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?

Given complete parameter schema, comprehensive annotations, and no output schema, the description covers purpose, usage, and workflow. It could mention error handling or limitations but is sufficient for a read-only tool.

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

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

Schema description coverage is 100%, with both parameters fully described. The description adds no new information about parameters beyond what the schema provides. Baseline 3 is appropriate.

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

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

Clearly states the tool resolves a CoDesign sharing URL into designs and screens with specific fields. Distinguishes from siblings like get_artboard_spec by being the first step.

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

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

Explicitly says to use this first when a task contains a CoDesign URL, then select a screen before calling get_artboard_spec. Also warns not to infer screens by cropping preview images.

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