Skip to main content
Glama

Krew Guru

Create seafarer profile draft from CV

create_seafarer_profile_draft

Turn a seafarer CV (plain text the seafarer pasted or shared: sea service records, ranks, vessels, certificates) into a Krew Guru profile draft. Sends a sign-in code and link to the email in the CV (or to the email argument if the CV has none); the seafarer opens the email and enters the code on krew.guru to save the profile; no tool accepts that code. Returns the same result as the Krew Guru website: status (verification_sent, email_required, not_a_cv), masked email, handoff_url for the seafarer, up to 5 matched_vacancies, user_message and next_actions. Contacts and document numbers are not returned. If status is email_required, ask the seafarer for an email and call again with the same text and the email argument. Drafts expire after 24 hours. The seafarer's name is saved in English letters, as in the passport: if the CV writes the name in another script, transliterate it and add the passport spelling to raw_cv_text. Limit: 6 CVs per 10 minutes. Use this when the seafarer asks to create or update a Krew Guru profile from a CV or to find jobs matching a CV. Do not use for CVs of other people without their consent, for non-maritime CVs, or for employer or vacancy data.

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": {
      "raw_cv_text": "<raw_cv_text>"
    },
    "name": "create_seafarer_profile_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailNoThe seafarer's own email. Only needed after status email_required; an email found in the CV is used first.
raw_cv_textYesFull CV text as provided by the seafarer, 40-48,000 characters, any language. Keep sea service records (vessel name, IMO, type, rank, dates).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations, it discloses the external email side effect, manual sign-in code handoff, 24-hour draft expiration, six-CVs-per-10-minutes limit, and omission of contacts and document numbers. Clarifying that no tool accepts the code and that the seafarer must act on krew.guru prevents incorrect assumptions about completing the workflow automatically.

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?

The purpose and principal side effect are front-loaded, and nearly every sentence supplies actionable workflow, output, or constraint information. The dense single paragraph and long enumeration of return fields reduce scannability, so grouping the workflow, statuses, and limits would improve structure without requiring more content.

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?

Because there is no output schema, the explicit statuses, return fields, sensitive-data omissions, and email_required recovery instructions are particularly valuable. Together with the handoff flow, expiration, rate limit, consent restrictions, and name-preparation rule, the definition supplies enough context to invoke the tool and handle its common outcomes correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds operational guidance that changes argument preparation: retry with the same raw_cv_text plus email after email_required, and transliterate non-Latin names while adding the passport spelling to raw_cv_text. These details go materially beyond repeating the schema's parameter descriptions.

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 opening sentence specifies both the transformation and resource: turning seafarer CV text into a Krew Guru profile draft, with typical CV contents identified. The CV-based creation and job-matching scope also distinguishes it from the draft-status, job-search, and job-detail siblings.

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?

An explicit 'Use this when' statement covers profile creation or update from a CV and CV-based job matching, while 'Do not use' excludes non-consensual third-party CVs, non-maritime CVs, and employer or vacancy data. It also gives a concrete retry path for email_required rather than leaving error recovery to inference.

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