Skip to main content
Glama

get next step

get_next_step
Read-onlyIdempotent

Show the user's next step in the job search as a card. With no scope it picks one from their data, with a line saying why: the setup trail while their roles aren't confirmed, else the pipeline's most urgent move, else the week's plan; use that for open questions like "what should I do next?" or "where do I start?". Scope setup is the setup trail in Compass OS: each setup stop (such as importing a resume) marked done or to do, with its effort, and what the next stop asks for; it never decides whether a request can be done, an unfinished stop blocks nothing. Scope today lists today's moves in the pipeline: counts (active, interviewing, offers, ready), the most urgent move (a follow-up, interview prep, or an application that's ready or missing a piece), the few after it, and any offer. Scope week summarizes the week: roles from the last scan worth a look, follow-ups due, interviews coming up, and one upkeep step; use it for "how's my week?" or "what needs me?". Read-only. Jobs updated from Gmail or Calendar show only in the card.

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_next_step"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoWhich card: leave empty to pick from the user's data (setup until the roles are confirmed, then today's pipeline move, else the week), with a line saying why; setup for the setup trail; today for today's pipeline moves; week for the week ahead

Output Schema

NameRequiredDescriptionDefault
textYesThe answer, or what was done, in plain words for the user: the same text as content
undoNoOn a saved write: its undo handle, for undo within 24 hours
widgetNoThe card the host draws with it, e.g. "pipeline"; "confirm" means a write waits for the user's Yes and nothing is saved yet

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent, so the description's real contribution is the non-obvious semantics: 'an unfinished stop blocks nothing' and that this card never gates requests, plus 'Jobs updated from Gmail or Calendar show only in the card.' That freshness caveat is exactly the kind of behavior an agent wouldn't otherwise know.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in sentence one, but the remainder is a 150-word semicolon-chained run-on that is hard to scan and overlaps heavily with the enum descriptions already in the schema. Information density is high enough to avoid a 2, but it needs restructuring into shorter lines.

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 single optional enum parameter with a documented default and an output schema, the description covers triggers, scope meanings, and caveats adequately. It over-describes return contents that the output schema already defines, which is wasteful rather than incomplete.

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

Parameters3/5

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

Schema description coverage is 100% and the enum values are documented, including the default-selection logic, so the description largely restates it. It does add a little by sketching what each scope's card contains, but no field/format detail beyond the schema.

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 first sentence names a concrete verb and resource ('show the user's next step in the job search as a card') and the scope clauses distinguish the three variants precisely, so an agent can tell this apart from list_pipeline or get_interview_prep 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 explicit trigger phrases ('what should I do next?', 'where do I start?', 'how's my week?') and explains which scope answers which question, which is strong routing guidance. It stops short of naming any alternative sibling tool or a when-not condition, so a 5 isn't warranted.

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