list_drawingsSummarize a project's drawings without their point lists: id, kind, color, width, point count and bounding box. Use this to find a stroke to erase; get_board carries the full geometry.
| Name | Required | Description | Default |
|---|---|---|---|
| projectId | Yes | Project id (uuid). |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true, matching the description's read-only nature. The description adds behavioral context beyond annotations by disclosing that point lists are intentionally omitted and summarizing what fields are returned, which helps set expectations for downstream use.
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 defines functionality and output fields, the second gives a concrete use case and names the alternative. Information is front-loaded and every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter read-only list tool with an output schema present, the description is fully sufficient. It explains what data is included, what is omitted, and when to use a sibling tool. No critical information 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?
Schema description coverage is 100%, with projectId described as 'Project id (uuid).' The tool description does not add additional parameter semantics, but the schema already adequately documents the only parameter, so a 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 uses a specific verb ('Summarize') and resource ('a project's drawings') while explicitly listing the returned fields, making the tool's function immediately understandable. It clearly distinguishes itself from get_board, which is named as carrying the full geometry.
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 this tool: 'Use this to find a stroke to erase.' It also names the alternative, get_board, and explains why you would choose that instead. This gives the agent clear routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool targets a distinct resource/action: board retrieval is split into JSON vs image with explicit cross-references, and drawing tools are separated from the generic update_board. Look-alikes like list_documents vs list_diagrams and publish_listing vs use_template are differentiated clearly.
Most tools follow a verb_noun pattern: create_project, list_documents, update_board, upsert_org_member. A few noun-only names like my_listings, project_file_counts and template_categories break the pattern, so naming is consistent but not uniform.
40 tools is well beyond the 25+ threshold for a single server, even though the domains are clustered into org/project/document/board/template areas. The large surface will make tool selection and onboarding heavier for an agent than necessary.
Core lifecycle coverage for org/project/document/board/template is mostly present, and update_board serves as a flexible escape hatch. However, the board API reads rectangle/diamond/ellipse/free-text drawings and groups/links but only offers explicit create/erase for strokes and arrows; paid template purchase/access is also left unclear.