Skip to main content
Glama

Prepare a follow-up to an earlier letter

create_followup_draft

Prepares a NEW letter to the same recipient as one of the person’s earlier letters (by reference), from the account’s saved return address, with the follow-up text you wrote with the person. It works exactly like prepare_certified_letter and returns a new review link: nothing from the earlier purchase carries over, and nothing is mailed or charged until the person reviews and pays for this new letter. Write the follow-up only after the person says no reply arrived or asks for one.

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": {
      "reference": "<reference>",
      "letter_text": "<letter_text>"
    },
    "name": "create_followup_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
serviceNoOptional. Defaults to CERTIFIED_ERR, whatever the earlier letter used.
referenceYesThe earlier letter’s Piloxa reference.
letter_textYesThe body of the follow-up you wrote with the person.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: the letter originates from the account's saved return address, returns a new review link, and 'nothing is mailed or charged until the person reviews and pays,' which is exactly the cost/side-effect detail an agent needs before invoking a non-readOnly tool. It also discloses that nothing from the earlier purchase carries over. The only gap is that it does not restate the openWorldHint consequence (the letter eventually mailing to a real external recipient) as plainly as it could.

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 core action and scope, then the alternative comparison, then the behavioral guarantees, then the usage gate, so an agent gets the essentials in the first clause. The second sentence is a long multi-clause run-on bundling the sibling comparison, the no-carryover rule, the billing gate, and the return value, which slightly dilutes scannability.

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?

No output schema exists, and the description compensates by naming the return value explicitly as a new review link. All three parameters are documented in the schema and reinforced in prose, and the mutation/charging behavior is covered. Only the service-enum interaction with the earlier letter's purchase is left slightly ambiguous.

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 100%, so the baseline is 3, but the description adds real meaning: 'reference' is not just an ID but the mechanism that fixes the recipient while carrying over no content, and 'letter_text' is scoped as text written with the person. It does not elaborate on the 'service' enum behavior beyond the schema's own default note; in fact 'nothing from the earlier purchase carries over' sits in mild tension with the schema's 'defaults to CERTIFIED_ERR, whatever the earlier letter used.'

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 ('Prepares a NEW letter'), pins down the recipient derivation ('same recipient as one of the person's earlier letters (by reference)'), and contrasts it with the sibling it mirrors ('works exactly like prepare_certified_letter'). An agent can distinguish it from prepare_certified_letter and the authorization/status tools without opening a schema.

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 gating condition for when to call it: 'Write the follow-up only after the person says no reply arrived or asks for one,' which also implicitly rules out using it for a first-contact letter. It names prepare_certified_letter as the behavioral analogue but never explicitly says 'for a brand-new letter to a different recipient, use prepare_certified_letter instead,' so the sibling routing is inferential rather than stated.

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