Skip to main content
Glama
Image Annotate MCP

Image Annotate MCP

by Thejiuyi

annotate_export

Export saved annotations as PNG overlays, Python coordinate constants with templates, or JSON/YAML payloads, returning file paths and generated source for agent use.

Instructions

Export a saved annotation. fmt='png' renders the base image with numbered outlines (for a multimodal agent to look at), 'py' emits coordinate constants plus a template map, 'json' / 'yaml' dump the payload. Returns file paths and, for 'py', the generated source.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "annotate_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
fmtNopng
nameYes
out_dirNo
image_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose the return contract (file paths, plus generated source for 'py'), which is genuinely useful, but it says nothing about where files land by default (out_dir defaults to null), whether existing files are overwritten, or what permissions/state are required for an export that writes to disk.

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?

Two dense sentences, front-loaded with the action and then the format semantics; every clause (including the parenthetical usage hint) carries information an agent needs.

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

Completeness4/5

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

Without an output schema, spelling out the return values is the right call and is done well, and the fmt semantics are fully covered. The remaining gap is the three undocumented non-format parameters and default output location, which matter for correctly invoking a file-writing tool.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate. It fully explains the most semantically loaded parameter (fmt, all four accepted values), but 'name', 'out_dir', and especially 'image_id' are never described anywhere, leaving a required parameter's meaning to inference.

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?

States a specific verb and resource ('Export a saved annotation') and enumerates the concrete output formats, which distinguishes it from a render/preview sibling. It does not explicitly name which sibling to use instead when the goal is only to display an annotation.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the parenthetical '(for a multimodal agent to look at)' hints at when to pick fmt='png', but there is no explicit when-to-use/when-not guidance or named alternative such as annotate_render.

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