Skip to main content
Glama

get_digest

Get new jobs matching your watchlist filters, ranked by fit score then keyword relevance, with known contacts at each company. Call fetch_jobs first to load today's postings.

Instructions

New jobs that pass the watchlist's filters, best first (fit score when scored, then keyword relevance), with people the user knows at each company. Call fetch_jobs first to pick up today's postings. This is for finding jobs to consider; for jobs already queued use list_queued_jobs, and for applications use list_applications. total is how many matched before the limit (jobs left out stay new for the next digest). not_scored, when set, says why a job is never fit-scored (a Hacker News post listing several roles). pace, unless the user turned it off: applications sent today against how many they aim for a day (daily) and the most (max); once met, suggest the rest wait for tomorrow, but never refuse to help.

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": "get_digest"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoThe most jobs to return, best first. Default: the watchlist's display.today (10 unless set; 25 when it's 0, for every match).
companyNoOnly this company's jobs (its name or board), best first: to pick among one company's roles, e.g. when it limits how many you can apply to. Empty: every company.
score_topNoHow many of the most relevant unscored jobs to fit-score against the resume with shortlist-ai first. 0 (the default) skips scoring; each job takes minutes on the local backend, so keep it small.
mark_shownNoMark the returned jobs as shown, so the next digest leaves them out. False to peek without changing anything.
include_seenNoAlso include jobs already shown in an earlier digest, not just new ones.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.0
    • addedInput schema / properties / company
      Added value: +{
      +  "default": "",
      +  "description": "Only this company's jobs (its name or board), best first: to pick among one company's roles, e.g. when it limits how many you can apply to. Empty: every company.",
      +  "title": "Company",
      +  "type": "string"
      +}
  2. Changed5 schema fields changedv0.5.0
    • addedInput schema / properties / limit / anyOf
      Added value: +[
      +  {
      +    "minimum": 1,
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / limit / default
      Previous value: -25New value: +null
    • changedInput schema / properties / limit / description
      Previous value: -"The most jobs to return, best first."New value: +"The most jobs to return, best first. Default: the watchlist's display.today (10 unless set; 25 when it's 0, for every match)."
    • removedInput schema / properties / limit / minimum
      Removed value: -1
    • removedInput schema / properties / limit / type
      Removed value: -"integer"
  3. Addedv0.3.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false / idempotentHint=false, and the description explains exactly why: mark_shown defaults to true so digest calls mutate state ('jobs left out stay new for the next digest'). It also documents total vs. limit semantics, the not_scored case, and the pace guidance including 'never refuse to help' — meaningful behavioral context beyond the annotation flags.

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 definition and ranking rule, then routing, then return-field semantics. Dense but each clause carries information; the closing pace/politeness paragraph is the weakest part and could be trimmed without loss.

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?

No output schema exists, so the description carries the burden of explaining return shape — it does so by defining total, not_scored, and pace. Combined with the mutation disclosure via mark_shown, an agent has everything needed to call this correctly.

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 baseline is 3; the description still adds value by explaining the consequence of limit ('jobs left out stay new for the next digest') and why not_scored entries exist (Hacker News posts listing several roles). It does not go beyond the schema for company/score_top/mark_shown, which are already well documented.

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+resource+scope: 'New jobs that pass the watchlist's filters, best first... with people the user knows at each company.' The ranking rule (fit score, then keyword relevance) makes the returned resource concrete, and it is immediately distinguishable from list_queued_jobs and list_applications which it names.

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?

Explicit prerequisites ('Call fetch_jobs first to pick up today's postings') and explicit exclusions ('for jobs already queued use list_queued_jobs, and for applications use list_applications'). It also frames intent: 'This is for finding jobs to consider'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.