Skip to main content
Glama
Image Annotate MCP

Image Annotate MCP

by Thejiuyi

annotate_wait

Wait for a user to save image annotations, then return exact boxes, points, polygons, names, and template images; treat pending as not saved and call again.

Instructions

Block until the user saves the annotation (or the timeout fires), then return the annotations: per image, a list of {index, name, type, box|point|points, template, hidden?}.

A status of 'pending' means the user has not saved yet -- that is NOT an error, just call annotate_wait again. Pass since_rev to only wait for saves newer than what you already have. Keep timeout_s below your MCP client's own tool timeout.

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": {
      "session": "<session>"
    },
    "name": "annotate_wait"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionYes
since_revNo
timeout_sNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses the blocking wait, the timeout escape, that 'pending' is not an error, and the shape of the returned payload. It leaves open what exactly is returned when the timeout fires rather than a save, and says nothing about session/auth expectations.

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 tight sentences, front-loaded with the blocking behavior and payload shape, then the pending/retry rule, then parameter guidance. Every sentence adds actionable information and nothing is redundant.

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?

There is no output schema, and the description compensates by spelling out the per-image record fields (index, name, type, box/point/points, template, hidden). Combined with the retry rule and timeout warning, this is nearly complete; the main remaining gap is the exact timeout return path.

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 coverage is 0%, so the description must compensate, and it does for two of three parameters: since_rev is explained as a revision watermark ('only wait for saves newer than what you already have') and timeout_s gets a concrete constraint relative to the MCP client timeout. 'session' is left unexplained, but its meaning is largely inferable from the tool family.

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 states a specific verb and behavior — 'Block until the user saves the annotation (or the timeout fires), then return the annotations' — plus the exact return structure. The blocking-until-save semantics are distinctive enough that an agent can separate this from siblings like annotate_status or annotate_list without opening their schemas.

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?

It gives explicit operational guidance: re-call annotate_wait when status is 'pending', use since_rev to wait only for newer saves, and keep timeout_s under the client's own tool timeout. It does not explicitly say when to prefer annotate_status or annotate_list instead, so it stops short of full when/when-not routing.

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