Open a scanned PDF or image for CAD conversion, rendering pages to PNG and returning sizes plus vector/raster status to guide next steps.
Open a scanned drawing (PDF or image) for CAD conversion. Pages are rendered to PNG. Returns page sizes and whether the PDF is vector (CAD-exported → scan_vector_import) or raster (read with scan_view).
| Name | Required | Description | Default |
|---|---|---|---|
| dpi | No | ||
| path | Yes | ||
| pages | No | ||
| scan_id | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full behavioral burden. It does disclose a real side effect (page rendering to PNG) and the return content (page sizes, vector/raster classification), which is useful. It omits whether files are written to disk, permission/format constraints, rate limits, and any session semantics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three compact sentences, front-loaded with the core action and outcome, then the branching rule. No filler, no restatement of the tool name.
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?
No output schema exists, and the description partially compensates by naming the return values (page sizes, vector vs raster flag). However, for a 4-parameter, 0%-coverage opening tool with no annotations, the missing semantics of scan_id and dpi leave an agent guessing about session reuse and render resolution.
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 0% across all four parameters, so the description is the only source of parameter meaning — yet it mentions none of path, dpi, pages, or scan_id explicitly. 'Pages are rendered' weakly hints at a pages selector, but dpi and especially scan_id (likely the session handle reused by the other scan_* tools) are left entirely 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?
States a specific verb (open) and resource (scanned drawing / PDF or image) plus the concrete outcome (pages rendered to PNG for CAD conversion). It also routes the agent to the correct sibling depending on file type (scan_vector_import vs scan_view), so it is distinguishable from siblings without opening schemas.
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 clearly frames this as the entry point that produces either a vector or raster result and names the correct follow-up tool for each branch. It does not state prerequisites (e.g., required format support, file size limits) or when to prefer scan_list instead, so it stops short of explicit when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.