Skip to main content
Glama

annotation

Create text, dimensions, leaders, and automate dimensioning workflows in AutoCAD drawings.

Instructions

Annotation: text, dimensions, leaders, and automatic dimension workflows.

Operations: create_text — data: {x, y, text, height?, rotation?, layer?} create_dimension_linear — data: {x1, y1, x2, y2, dim_x, dim_y} create_dimension_aligned — data: {x1, y1, x2, y2, offset} create_dimension_angular — data: {cx, cy, x1, y1, x2, y2} create_dimension_radius — data: {cx, cy, radius, angle} create_leader — data: {points: [[x,y],...], text} detect_parts — read-only geometry clustering; data: {source_layers?, gap_tolerance?, include_screenshot?} plan_dimensions — preview a plan without editing; data: {target_part_id?, entity_ids?, region?, region_mode?, selection?, use_current_selection?, source_layers?, profile?, dimension_layer?, include_overall?, include_features?, include_holes?, include_arcs?, include_centers?, clear_existing?} commit_dimension_plan — commit an approved plan; data: {plan_id, expected_revision, ...} auto_dimension — detect, plan, and commit in one request. It accepts target_part_id, entity_ids, region, region_mode, selection='current' or use_current_selection, source_layers, dimension_layer, profile, include_overall, include_features, include_holes, include_arcs, include_centers, clear_existing, include_screenshot. batch_create_dimensions — commit data.dimensions in one request, one Undo group, and one final Regen where the backend supports it. dimension_profiles — data: {action: list|get|save|delete, ...} audit_dimensions — read-only dimension quality audit; data: {profile?, dimension_layer?, include_screenshot?} repair_dimension_layout — apply a fresh audit's safe repairs; data: {audit_id, issue_ids?, spacing?}

Automatic-dimension selectors are mutually exclusive: target_part_id, entity_ids, region, or selection='current'. Dimension results include created_count, dimension_types, selection_scope, scan counters, commit_engine, regen_count, and timings_ms when the backend can provide those values.

Performance rule: when two or more dimensions are needed, use annotation_batch_create_dimensions or annotation_auto_dimension once. Do not call create_dimension_* repeatedly.

Performance rule: pass region, entity_ids, or selection='current' whenever possible. After annotation_detect_parts, reuse geometry_cache_token together with target_part_id so the same full drawing is not exported twice.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
operationYes
include_screenshotNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior3/5

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

The description identifies read-only sub-operations (detect_parts, audit_dimensions) and mentions behavior like undo groups and regen for batch operations. Beyond the annotations (readOnlyHint=false), it adds context but does not fully disclose error states, permission requirements, or the full scope of effects, especially for commit operations.

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

Conciseness3/5

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

The description is structured as a bullet list of operations, which aids scanning. However, it is quite long and includes repetitive performance rules at the end. Some information could be condensed without loss of clarity.

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

Completeness3/5

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

Given the complexity of the tool (many operations) and minimal schema, the description covers the main operations and provides performance rules. However, it omits how output schema looks, error handling, and the relationship to sibling tools. It is adequate but not fully comprehensive.

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?

With the input schema having 0% parameter description coverage, the description compensates by listing expected data keys for each operation (e.g., create_text expects x, y, text, etc.). This adds significant meaning beyond the generic schema. Some operations are vaguely defined (e.g., dimension_profiles has 'action' but no details), so it's not perfect.

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

Purpose4/5

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

The description clearly states the tool's domain—text, dimensions, leaders, and automatic dimension workflows. It lists multiple specific operations, making the purpose evident. However, it does not differentiate this parent tool from sibling tools that seem to provide the same sub-operations directly, which could cause confusion.

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

Usage Guidelines4/5

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

The description includes explicit performance rules (e.g., use batch or auto_dimension for multiple dimensions, pass region when possible) and notes mutual exclusivity of selection parameters. These provide actionable guidance for efficient tool use. However, it lacks guidance on when to use this parent tool versus the sibling tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sontakmtp-cell/autocad-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server