Canvs

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

The annotations only indicate non-readonly and non-destructive, which is consistent with the description's 'creates' language. The description adds meaningful behavioral context beyond the annotations: the room_id behavior, arrow auto-binding within 30px, rich-text HTML subset, and color handling. This goes well beyond the minimal hints, though it doesn't cover every edge case.

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 fairly long but well-structured with clear section headers (Rich text, TEXT IN SHAPES, ARROWS, Colors). The main purpose is front-loaded. Some redundancy exists with the schema (e.g., the HTML subset is repeated), but each section provides useful guidance. Overall, it earns its length without being bloated.

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

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

Given the tool's complexity (multiple element types, rich text, arrow binding, canvas creation), the description covers key aspects well: usage context, element types, rich-text constraints, arrow positioning, and color format. An output schema exists, so return values are not needed. Minor gaps include lack of coordinate system explanation and the textAlign reference without a schema parameter, but the description is still highly complete for a complex tool.

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

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

Schema coverage is 100%, so baseline is 3. The description enriches this by explaining when room_id should be used, elaborating on the element types and their inferred defaults, explaining containerId for bound text, and detailing arrow binding behavior. It adds value over the schema descriptions, though some details (like textAlign) are mentioned in the description but not present as a schema property.

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 creates elements on a canvas and distinguishes between creating a new canvas or adding to an existing one via room_id. It explicitly names the sibling tool add_elements_from_mermaid and explains when to use that instead, making the purpose and scope 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?

Provides explicit 'when to use' guidance with concrete use cases (wireframes, UI mockups, freeform illustrations, etc.) and directly says 'For diagrams Mermaid can express, use add_elements_from_mermaid instead.' It also explains when to pass room_id versus omit it, giving clear 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 the annotations by disclosing that a new canvas is created if room_id is omitted, but elements are added to an existing canvas if room_id is provided. It also notes that config.curve is handled server-side. This adds meaningful behavioral context beyond the minimal readOnly/destructive hints. It does not mention error handling or whether elements are appended vs. replaced, but key behavior is covered.

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 well-organized: a clear first sentence, a preference statement, a list of supported diagram types, and an example. The list is long but necessary given the many Mermaid diagram types. No filler, but it could arguably be trimmed (e.g., move the full list to a separate reference). It earns a 4, not a 5, due to the length.

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 tool's purpose, when to use it, conditional behavior (new vs. existing canvas), supported Mermaid diagram types, and includes an example. An output schema exists, so return values need not be detailed. It misses error-handling and edge cases (e.g., invalid Mermaid), but it is fairly complete for the tool's complexity.

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

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

Schema description coverage is 100%, so the baseline is 3. The tool description adds a few useful notes (e.g., 'prefer converting compatible user requests into Mermaid') but mostly repeats what the schema already states for parameters like room_id and timeout. It does not significantly enrich parameter understanding beyond the schema.

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

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

The description clearly states the tool 'creates diagram elements from a Mermaid definition' and explains the key conditional behavior (new canvas vs. existing canvas based on room_id). It distinguishes itself from the sibling add_elements by specifying that this tool works from Mermaid and is preferred for certain cases.

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 names an alternative (add_elements) and states when this tool is preferred: 'for new diagrams and large changes to existing diagrams whenever the content can be represented in Mermaid.' However, it does not explicitly state when NOT to use it (e.g., for small edits), so it falls just 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?

Annotations already mark destructiveHint=true, and the description explicitly says 'delete'. It adds the dependency on room_id from a prior result, but doesn't detail irreversibility or side effects. With annotations present, this is adequate.

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

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

The description is two sentences, front-loaded with the verb and resource, and contains no unnecessary 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?

For a simple delete tool with full schema annotations and an output schema, the description covers the necessary usage context and prerequisites. No significant 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 coverage is 100% and both parameters are well-described in the schema. The description only restates the ids and room_id information, adding no new semantic value.

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

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

The description clearly states the tool deletes elements from a canvas, using a specific verb and resource. This distinguishes it from sibling tools like add_elements and update_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?

It provides the prerequisite of room_id from a previous Canvs tool result and instructs the user to pass an ids array. Though it doesn't explicitly mention alternatives, the context is clear for a delete operation.

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 and destructiveHint=false. The description adds useful context about the guide's content and purpose, but doesn't disclose additional behavioral traits such as output format or limitations. Given the strong annotation coverage, this is sufficient.

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

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

The description is two sentences, front-loaded with the primary purpose, and includes a clear usage directive. Every sentence adds value with no redundant or irrelevant 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?

Given the tool's simplicity (no params, output schema provided), the description is complete. It explains what the guidance covers and when to use it, while the output schema handles return value details. No additional context is needed 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 description need not explain parameter details. The schema contains no properties, and the description clarifies the tool's purpose without needing to compensate for missing parameter information. Baseline 4 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 clearly states the tool 'Returns guidance on diagram-creation workflow and tool selection,' specifying the exact resource and action. It also distinguishes from sibling tools like add_elements or query_elements by focusing on advisory content rather than element manipulation.

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 to 'Consult before building complex diagrams,' providing clear usage context. It also outlines the key topics covered (Mermaid vs. manual creation, iteration workflow), but does not explicitly state when not to use it or mention 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, so the read-only nature is known. The description adds valuable behavioral context not in annotations: the requirement that a browser must have the canvas open, and the specific error/retry flow. It does not over-explain.

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 front-loaded with the core purpose, followed by prerequisite, usage context, and error handling. Each sentence contributes meaning, though some information (room_id requirement) is also present in the schema, making it slightly 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?

Given that an output schema exists and annotations cover safety, the description adequately covers the tool's purpose, prerequisites, related tools, and a key failure mode. It is complete enough for an agent to invoke correctly without 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% with descriptions for all parameters, including a detailed room_id extraction pattern. The description only restates that room_id is required and that there are optional filters, adding minimal semantic value beyond the schema. Baseline of 3 is appropriate.

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

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

The description clearly states the tool's purpose: querying elements on a canvas with optional filters. It also distinguishes itself from siblings by explicitly positioning it as a precursor to update_elements for small edits to existing diagrams.

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 guidance: requires a room_id from a previous Canvs tool result, should be used before update_elements, and describes the browser-open prerequisite and how to handle the error if the browser is not open. This is well beyond minimal 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?

Annotations already indicate this is a destructive/mutating operation (readOnlyHint=false, destructiveHint=true). The description adds critical patch semantics: 'only id is required; all other fields are optional patch fields' and 'elements omitted from the request remain unchanged.' These go beyond the annotations and clarify exactly how the mutation behaves.

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 — five sentences, with key information front-loaded. The critical 'IMPORTANT' caveat is highlighted, and every sentence adds value (purpose, prerequisite, input format, patch behavior, usage context). No fluff or 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 the tool's moderate complexity (2 outer params, nested elements objects), the description covers the essential workflow: requires room_id from a previous Canvs result, passes a patch array, and is preferred for small edits after query_elements. It omits failure behavior but is otherwise complete for practical use, especially since an output schema exists.

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

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

Schema has 100% coverage, so the baseline is 3. The description reinforces the patch nature of 'elements' and emphasizes that fields are optional, but the schema already describes each property and the items-level note 'only id is required.' No additional meaning beyond the schema is added.

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 'Update elements on a canvas,' using a specific verb and resource. It clearly distinguishes from siblings by emphasizing 'existing diagrams' and 'small edits' (rename/move/restyle), contrasting with add_elements and delete_elements. This makes the tool's 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?

Provides explicit when-to-use guidance: 'Prefer this tool for SMALL edits to existing diagrams... typically after query_elements.' It also requires room_id from a previous result, covering prerequisites. It stakes a clear position among siblings, though it doesn't explicitly name build/delete alternatives.

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