Skip to main content
Glama

generate_signature

Signature Generator — Write a name out in a handwriting style and return it as a PNG with a see-through background, so a later step can stamp it onto a PDF. [category: generate]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesOne line, up to 64 characters. Line breaks and tabs become spaces, and a leading '@' is stripped — ImageMagick reads a leading '@' as 'go and read this file', so it is never passed through.
colorNoA hex colour (#1a1a2e or #fff, with or without the '#', optionally with an alpha pair) or a colour name such as black or navy. A colour we cannot read is refused, and so is ink that would not show, such as transparent.#1a1a2e
styleNoWhich handwriting face to use: Script is Dancing Script, Elegant is Great Vibes, Handwritten is Pacifico and Bold is Lobster, the faces the web page draws. When that face is not installed on our server, another handwriting face is drawn in its place, never a plain block font, and the X-JE-Font-Substituted response header says so. Only when no handwriting face is installed does the request fail.script
paddingNoEmpty space left around the signature, so it does not sit flush against the edge when it is stamped onto something.
fontSizeNoOut-of-range values are pulled back to the nearest allowed value rather than refused.
backgroundNo'transparent' is what makes the result stampable onto a PDF or a photo. Give a colour instead, as hex or a name such as white, if you want it on a solid card. A colour we cannot read is refused rather than turned transparent.transparent

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / background / description
      Previous value: -"'transparent' is what makes the result stampable onto a PDF or a photo. Give a hex colour instead if you want it on a solid card."New value: +"'transparent' is what makes the result stampable onto a PDF or a photo. Give a colour instead, as hex or a name such as white, if you want it on a solid card. A colour we cannot read is refused rather than turned transparent."
    • changedInput schema / properties / color / description
      Previous value: -"A hex colour, with or without the leading '#'. Anything we cannot read reverts to the default ink."New value: +"A hex colour (#1a1a2e or #fff, with or without the '#', optionally with an alpha pair) or a colour name such as black or navy. A colour we cannot read is refused, and so is ink that would not show, such as transparent."
    • changedInput schema / properties / style / description
      Previous value: -"Which handwriting face to use. If the chosen face is not installed on the server the request fails and says so, rather than handing back a 'signature' in a plain block font."New value: +"Which handwriting face to use: Script is Dancing Script, Elegant is Great Vibes, Handwritten is Pacifico and Bold is Lobster, the faces the web page draws. When that face is not installed on our server, another handwriting face is drawn in its place, never a plain block font, and the X-JE-Font-Substituted response header says so. Only when no handwriting face is installed does the request fail."
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

With only basic annotations, the definition adds valuable behavioral detail: the PNG has a transparent background, invalid colors are refused, out-of-range font sizes are clamped, and an unavailable handwriting font triggers substitution via a response header. It does not mention output encoding/delivery, but no annotation contradiction exists.

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?

The main description is two sentences that front-load the core behavior and downstream purpose, with a category tag at the end. The longer parameter descriptions are organized by field and each sentence carries semantic value.

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?

For a generator with six parameters and no output schema, the definition gives the output format (PNG, transparent background) and covers failure behavior via parameter descriptions. It does not state how the PNG is delivered (path, data URL, bytes), which is the main remaining gap.

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 100%, so each of the six parameters is documented in the input schema with defaults, constraints, and edge cases. The top-level description adds no additional parameter relationships or examples, matching the baseline for high schema coverage.

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 resource: write a name in a handwriting style and return it as a transparent-background PNG for later stamping onto a PDF. It clearly distinguishes generate_signature from the many sibling generators and from the esign_* tools that place signatures.

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 the intended usage context ('so a later step can stamp it onto a PDF'), which tells an agent this tool produces an intermediate asset rather than a finished document. It does not explicitly name the sibling esign_place/pdf_watermark as the downstream alternative, so there is a small exclusion gap.

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.

Resources