Skip to main content
Glama

Write a cover letter

generateCoverLetter

Writes a cover letter from the candidate's resume draft for one job, in the candidate's own voice, using only facts in the draft, saves it to their cover letters (listCoverLetters) and returns the text, its letterId and a PDF link valid for an hour. Give it the job description text, or the jobId of a Clera role from searchCleraRoles / listMatches. External board listings from searchJobs have no Clera jobId: paste their description instead. instruction passes on what the candidate wants different ("shorter", "lead with the payments work"); editCoverLetter changes the wording of a saved letter by hand.

Clera privately records this tool's inputs and results for usage tracking and support.

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": "generateCoverLetter"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoA name to save it under, e.g. the role and company.
jobIdNoA Clera role's jobId (searchCleraRoles / listMatches) instead of pasted text. Not for external board listings.
instructionNoWhat the candidate wants from this letter, in their words.
jobDescriptionNoThe job post text.

Output Schema

NameRequiredDescriptionDefault
contentYes
letterIdYes
expiresAtYes
signedUrlYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover the generic profile (not read-only, not open-world, not idempotent, not destructive); the description adds real behavioral context: a letter is persisted and appears in listCoverLetters, a PDF link expires after an hour, generation is constrained to facts present in the draft, and inputs/results are recorded for usage tracking. These are non-obvious traits an agent would otherwise have to discover by calling.

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 outcome and its constraints, then input routing, then the disambiguation, then the privacy note — a sensible order with no filler sentences. It is a dense single block with several parentheticals, so a minor structural cost, but very little that could be cut.

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?

For a generative, persisting tool with four optional parameters, the description covers source constraints, input alternatives, side effects, return values, link expiry, and the sibling for editing. With an output schema present it does not need to enumerate the response shape, so nothing material is missing.

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 the relationship the schema does not state: jobId and jobDescription are alternative ways to supply the same job, with jobId valid only for Clera roles. It also clarifies instruction's intent ('what the candidate wants different') with examples, going beyond the schema's own wording.

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 (writes a cover letter) plus the source material (the candidate's resume draft for one job), the grounding constraint (only facts in the draft), the persistence side effect (saves to cover letters), and the return payload (text, letterId, one-hour PDF link). An agent can distinguish it from editCoverLetter and generateApplicationDocuments from the description alone.

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?

Gives explicit input routing: pass jobDescription text, or jobId from searchCleraRoles/listMatches, and explicitly excludes external board listings from searchJobs with the fallback (paste the description). It also names the alternative for a different need — editCoverLetter for hand-editing saved wording — and explains what instruction is for with concrete examples.

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