Skip to main content
Glama
Sign In

Sendhour

by com.sendhour
OverviewDiscussionsAdmin

Add text to a photo

add_text_to_photo

Draw a heading and text on a photo already in Sendhour (from upload_media_from_url), the way Sendhour's studio draws slideshow slides, in the colours, box and place you choose (to match a slideshow you are copying, give its text colour, box colour and height), and get the new photo's media id (the original stays). The heading is drawn bigger and bold above the text. In the text, a line break starts a new line and a blank line (two line breaks) starts a new paragraph with a gap above it. Text that is too long is drawn smaller to fit TikTok's safe area. Free. Use it to make each slide of a photo slideshow, then pass the new ids to schedule_post or create_draft.

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": {
      "media_id": "<media_id>"
    },
    "name": "add_text_to_photo"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoThe text under the heading, up to 600 characters. Blank line = new paragraph.
styleNoHow the text looks. Every field is optional.
headingNoOptional heading, up to 150 characters, drawn bigger and bold
media_idYesA photo from upload_media_from_url

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnly=false, destructive=false, openWorld=false; the description adds real behavior: a new photo is created while "the original stays" (consistent with destructiveHint=false), the operation is free, long text is auto-shrunk to TikTok's safe area, and newline/paragraph semantics are spelled out. That is substantial context the annotations do not carry.

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

Conciseness4/5

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

Front-loaded with the action and result, and every sentence carries information (cost, overflow behavior, paragraph rules, downstream routing). It is a dense single block with a slightly run-on opening clause, but no filler.

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?

There is no output schema, yet the description explicitly states the return value (the new photo's media id) and that the original is preserved. Combined with the fully documented nested style object and the slideshow/scheduling workflow, an agent has everything needed to call it correctly.

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 already 100%, so the baseline is 3, but the description adds meaning on top: the heading is "drawn bigger and bold above the text", the matching-a-slideshow recipe maps to text colour, box colour and height (text_color, box_color, y), and line-break behavior is clarified. It does not explain preset/position interactions beyond what the schema enums already say.

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?

States a specific verb and resource ("Draw a heading and text on a photo already in Sendhour") plus the scope of the input (from upload_media_from_url) and the output (a new media id). This clearly separates it from edit_slide_text, which operates on slideshow slides rather than producing a new photo.

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?

Gives an explicit usage scenario ("Use it to make each slide of a photo slideshow") and routes the agent downstream to schedule_post or create_draft with the returned ids, plus a matching hint for copying a slideshow's colours. It stops short of an explicit exclusion such as when to prefer edit_slide_text or swap_slide_photo instead.

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

All Sendhour toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources