Skip to main content
Glama

Describe a PDF drawing

describe_pdf
Read-only

Return a structured JSON summary of a PDF drawing — units (points), bounding box, layers, per-type entity counts, the text it contains, and what was skipped (images, shadings, transparency). Use this for structural questions about a PDF without rendering it. For a DXF use describe_dxf; if you do not know the format, use describe_doc. Covers the whole drawing by default, including every page of a multi-page PDF; pass space (a name from the reply's spaces) to scope it to one page or sheet. When the user wants to see or explore the drawing themselves, prefer view_dxf (interactive viewer) — if your platform gates it behind user approval, offer it and ask rather than substituting a static render.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
spaceNoWhich space to work on: "Model" (a PDF's page 1, a DXF's model space) or a page/layout name as listed in a describe reply's "spaces". Describe omits it for the whole drawing; render defaults to the first space.
sourceYesA publicly reachable http(s) URL, or inline DXF text. A PDF is binary, so it must be a URL — inline PDF bytes are refused. (This is a hosted server — local file paths are not available; use the npx @aspicio/mcp local server for files on disk.)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
sizeYesBounding-box size in drawing units, null when empty
spaceYesWhich space this summary is scoped to, or null when it covers the whole drawing (bounds/size then describe spaces[0], the space render returns)
textsYesUnique TEXT/MTEXT strings, blocks included
unitsYesDrawing-unit label (e.g. "mm"), "" when unitless
boundsYesWorld-space extents, null for an empty drawing
formatYesWhich format was read ("dxf", "pdf")
layersYes
spacesYesEvery space in the drawing (a PDF's pages, a DXF's model space and layouts), model space first. These do not sum to entityCount: a DXF sheet's viewports re-show model geometry, so an entity can be drawn in two spaces while existing once
entityCountYes
entityTypesYesTop-level entities per DXF type
unsupportedYesPer-kind counts of what was skipped
segmentCountYes

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds meaningful behavioral context beyond annotations: it covers the whole drawing by default (including every page of multi-page PDFs), explains the 'space' parameter's scoping effect, and discloses what content is skipped (images, shadings, transparency). This is more than the annotations provide but doesn't go into all edge behaviors (e.g., what happens on invalid source). A 4 is appropriate.

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

Conciseness5/5

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

Four sentences, each dense with unique information: what it returns, when to use, alternatives, default behavior, and viewer preference. No fluff or repetition of structured fields. The front-loaded first sentence gives immediate clarity.

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

Completeness5/5

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

The description is fully self-contained for a read-only structural query tool with an output schema. It explains the return payload, default vs scoped behavior, handling of multi-page PDFs, and points to alternatives. The output schema exists, so return-value details are covered there. No significant contextual gap remains.

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

Parameters4/5

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 adds real value for the 'space' parameter by clarifying it takes a name from the reply's 'spaces' and that omitting it means the whole drawing, which the schema does not say. For 'source', the schema already covers the URL/inline refusal, and the description doesn't repeat it. The added scoping semantics justify a 4.

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

Purpose5/5

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

The description opens with a specific verb and resource: 'Return a structured JSON summary of a PDF drawing' and instantly enumerates the returned fields (units, bounding box, layers, entity counts, text, skipped content). It explicitly distinguishes from siblings: 'For a DXF use describe_dxf; if you do not know the format, use describe_doc.' This is a model example of purpose clarity.

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

Usage Guidelines5/5

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

Usage guidance is explicit and actionable: 'Use this for structural questions about a PDF without rendering it' immediately sets the primary use case. It provides clear alternatives with conditions ('For a DXF use describe_dxf; if you do not know the format, use describe_doc') and even advises preferring an interactive viewer (view_dxf) when the user wants to explore the drawing, with a caveat about platform approval. This is textbook when-to-use vs alternatives.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: describe for structural facts, render for static images, view for interactive exploration, and format variants (doc/dxf/pdf) are explicitly disambiguated via format detection. The internal load_dxf_for_viewer is clearly marked as widget-only, so no real ambiguity exists.

Naming Consistency4/5

The naming follows a consistent verb_format pattern for describe_* and render_* tools, and view_dxf fits the verb_noun convention. Minor deviations include 'doc' as a generic format label, 'load_dxf_for_viewer' with a purpose suffix, and view_dxf also handling PDF despite the DXF-specific name.

Tool Count5/5

8 tools is well-scoped for a drawing inspection server: three describe variants, three render variants, one interactive viewer, and one internal loader. Each tool earns its place without redundancy or bloat.

Completeness5/5

The tool surface fully covers its read-only domain: structural description, visual rendering, and interactive exploration for both DXF and PDF formats. Missing operations like editing or conversion are outside the intended purpose, and the internal loading is appropriately handled by the viewer widget.