Skip to main content
Glama

update_cover_letter

Save edits onto an existing cover letter. Pass the version from the latest get_cover_letter, create_cover_letter, or duplicate_cover_letter response in this turn. On cover_letter_invalid, fix validation and retry with the same version. On cover_letter_conflict, call get_cover_letter again. The server owns id, source, createdAt, updatedAt, openedAt, jobTitle, and the tailoring object. To set the company the job is at, pass company and, when you know the company website, companyDomain; leave both out to keep the stored company. company or companyDomain inside the document body is ignored. A bad value returns invalid_input. recipient.company in the letter is separate and never sets the logo.

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": {
      "coverLetterId": "<coverLetterId>",
      "version": "<version>",
      "coverLetter": "<coverLetter>"
    },
    "name": "update_cover_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyNoThe company the job is at, at most 200 characters. An empty string removes the company and its domain.
versionYes
coverLetterYes
companyDomainNoThe company website as a bare hostname, such as lucid.co (no https://, path or port). Sets the logo. Needs company.
coverLetterIdYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare it is a non-destructive, closed-world write; the description goes well beyond by disclosing optimistic concurrency via version, enumerating server-owned fields (id, source, timestamps, jobTitle, tailoring), naming error codes, and flagging that company/companyDomain inside the document body are silently ignored. These are non-obvious behavioral traits an agent could not infer from annotations.

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 purpose, then version handling, then error recovery, then field ownership — a logical order with no filler sentences. It is on the dense side at roughly nine sentences, but each one carries distinct operational information; the closing note about recipient.company is the only line that feels like a late addendum.

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 mutating tool with a nested document body, no output schema, and a concurrency token, the definition covers prerequisites, failure modes, field ownership, and side effects on the stored company and logo. The one omission is what a successful call returns (presumably a new version plus the saved letter), which matters because the agent must know whether to reuse the version afterward.

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 only 40% (company and companyDomain are documented, version/coverLetter/coverLetterId are bare), and the description compensates substantially: it explains version's provenance and concurrency role, what coverLetter contains and which body fields are ignored, and the company/companyDomain pairing rule including the empty-string removal case. coverLetterId is never explicitly characterized beyond being implied by "existing cover letter," which is the only remaining gap.

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?

Opens with a specific verb and resource ("Save edits onto an existing cover letter") and implicitly separates itself from create_cover_letter and duplicate_cover_letter by requiring an existing letter plus a version token. An agent can distinguish it from every sibling 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the prerequisite (version from the latest get_cover_letter, create_cover_letter, or duplicate_cover_letter response in this turn), the recovery path for each named error (retry same version on cover_letter_invalid, call get_cover_letter on cover_letter_conflict), and the keep-vs-set condition for company fields. This is when-to-use guidance at the level of individual call decisions.

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