Skip to main content
Glama

Save a template

save_template

Create a template (omit template_id) or update one (every plan). Changing the markdown saves a new version; older versions are kept. Use {{ variable_name }} placeholders for values that change per document, e.g. [[signature: {{ client_name }} <{{ client_email }}>]].

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
nameNoRequired when creating.
api_keyNoAn md2sign API key. When given, this call uses that key's account even if the connection is signed in as someone else, so pass it on every call when your human has more than one md2sign account (for example two businesses). Also use it if your MCP client cannot send an "Authorization: Bearer <api_key>" header.
markdownNoFull template markdown. Required when creating.
change_noteNoWhat changed in this version.
descriptionNoShort note on what the template is for, shown in the template list.
template_idNoOmit to create a new template.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / api_key / description
      Previous value: -"Your md2sign API key. Only needed if your MCP client cannot send an \"Authorization: Bearer <api_key>\" header."New value: +"An md2sign API key. When given, this call uses that key's account even if the connection is signed in as someone else, so pass it on every call when your human has more than one md2sign account (for example two businesses). Also use it if your MCP client cannot send an \"Authorization: Bearer <api_key>\" header."
  2. Changed1 schema field changed
    • addedInput schema / properties / description / description
      Added value: +"Short note on what the template is for, shown in the template list."
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the safety profile is known. The description adds genuinely non-obvious behavior beyond them: editing markdown does not overwrite, it appends a new version while older versions are kept — the key fact for an agent deciding whether a save is safe. It also discloses the placeholder convention that governs valid markdown content.

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?

Three tight sentences, front-loaded with the create-vs-update decision, then versioning behavior, then the placeholder convention — good ordering with no filler. The parenthetical "(every plan)" is cryptic and slightly interrupts an otherwise clean line.

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?

With no output schema, an agent could still wish to know what comes back (presumably a template_id) and whether an update replaces the full markdown or patches it, but the versioning note implicitly answers the latter. Given all six parameters are fully described in the schema and the tool is non-destructive, coverage is close to complete.

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 coverage is 100%, so all six parameters (including the api_key multi-account guidance) are already documented; baseline is 3. The description's template_id/markdown note largely restates what the schema says, and the placeholder syntax, while useful, is about markdown content rather than adding meaning to a specific parameter.

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?

"Create a template (omit template_id) or update one" gives a specific verb+resource and disambiguates the two modes with the controlling parameter, so an agent knows exactly what the call does. It does not name any sibling (e.g. delete_template, get_template) as an alternative, but the resource is unambiguous enough that this costs little.

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?

Explicit routing rule: omit template_id to create, supply it to update. That is a real when-to-use condition tied to a parameter rather than vague prose. It stops short of saying when NOT to use this tool (e.g. use validate_markdown or render_preview first to check the markdown before saving).

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.