ResumeQuick

Get the next step

get_next_step

Read-only

Get the user's one next step in the job search — the same step the ResumeQuick home screen shows — with the reason from their data and, when the step is about a vacancy, that vacancy and the step inside it (tailor, cover_letter, apply, interview), and app_url — the screen in ResumeQuick where the step is done. After an application the vacancy has no step until the employer answers; the step moves to new radar matches or another analysed vacancy. Args: {}.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`step`	Yes	The user's one next step, the same one the home screen shows: paused (the user paused the search until a date; there is no step until it ends or they resume it), resume (the active resume lists no work experience and the user has never edited it; adding a job or any edit by the user clears it), radar (the job radar is off, nothing is analysed yet, or it has new matches), interview_prep (a vacancy moved to Interview within 14 days), vacancy (an analysis from the last 72 hours, not applied to), saved (saved radar matches not analysed), revisit (the best-scored analysis of the last 14 days not applied to), cycle (none of these).
`match`	No	The radar match the step is about. On the saved step: the strongest one saved, not analysed and not known to be closed — the same one the end of the radar deck offers. On the radar step with new matches: the strongest one the user has not judged yet, which save_radar_match keeps. Null otherwise.
`radar`	Yes	off (the automatic daily search is off — get_radar_status.auto_search_enabled is false; matches already found stay), searching (on, with no new or saved match in the working list), matches (on, with at least one).
`reason`	Yes	Why this step, from the user's data.
`app_url`	No	Full link to step_path on the ResumeQuick site, opened after signing in to this account; null when paused.
`vacancy`	No	The vacancy the step is about (vacancy, revisit, interview_prep); null otherwise.
`step_path`	No	Path on the ResumeQuick site where the step is done, the same screen the home card opens; null when paused.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 19, 2026

addedOutput schema / properties / app_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Full link to step_path on the ResumeQuick site, opened after signing in to this account; null when paused.",
+  "title": "App Url"
+}

changedOutput schema / properties / radar / description

Previous value: -"off (the automatic daily search is off — get_radar_status.auto_search_enabled is false; matches already found stay), searching (on, radar_matches is 0), matches (on, radar_matches above 0)."New value: +"off (the automatic daily search is off — get_radar_status.auto_search_enabled is false; matches already found stay), searching (on, with no new or saved match in the working list), matches (on, with at least one)."

removedOutput schema / properties / radar_matches

Removed value: -{
-  "description": "Radar matches still in the working list: new ones, whether already shown or still waiting in the pool, and saved ones; skipped, deferred and archived ones are not counted. An input to the step: the job the step is about is in match and reason, which state no count.",
-  "title": "Radar Matches",
-  "type": "integer"
-}

removedOutput schema / properties / saved_to_analyze

Removed value: -{
-  "description": "Saved radar matches with no analysis. An input to the step: the one saved job the step names is in match and reason, which state no count.",
-  "title": "Saved To Analyze",
-  "type": "integer"
-}

changedOutput schema / required

Previous value: -[
-  "step",
-  "reason",
-  "radar",
-  "radar_matches",
-  "saved_to_analyze"
-]New value: +[
+  "step",
+  "reason",
+  "radar"
+]

Changed2 schema fields changedOct 17, 2026

changedOutput schema / properties / radar_matches / description

Previous value: -"Radar matches still in the working list: new ones, whether already shown or still waiting in the pool, and saved ones; skipped, deferred and archived ones are not counted."New value: +"Radar matches still in the working list: new ones, whether already shown or still waiting in the pool, and saved ones; skipped, deferred and archived ones are not counted. An input to the step: the job the step is about is in match and reason, which state no count."

changedOutput schema / properties / saved_to_analyze / description

Previous value: -"Saved radar matches with no analysis."New value: +"Saved radar matches with no analysis. An input to the step: the one saved job the step names is in match and reason, which state no count."

First observedOct 15, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false, destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the vacancy-step state machine (no step after applying until the employer answers, then it moves to new radar matches or another analysed vacancy) and the app_url deep link for where the step is performed.

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-loads the core purpose in the opening clause, then layers on the payload detail and lifecycle rule. The single dense sentence is a bit run-on and "Args: {}" is filler for an empty schema, but there is no padding or repetition.

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?

An output schema exists, so return values need not be explained, yet the description still characterizes the key fields (reason from their data, the vacancy and its inner step, app_url). With zero parameters and a declared read-only profile, 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?

There are zero parameters and schema description coverage is 100%, so the baseline is 4; nothing about parameter meaning needs compensating. The trailing "Args: {}" adds nothing but also does no harm.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — "Get the user's one next step in the job search" — and pins it to the ResumeQuick home screen, so the agent knows exactly what this returns. It also enumerates the returned shape (step, reason, vacancy, step type, app_url). It never contrasts itself with adjacent readers like get_coach_plan or get_recent_activity, so sibling differentiation is implicit rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied — this is the canonical 'what should I do next' call — but the description never says when to prefer it over get_coach_plan, get_recent_activity, or get_radar_matches, nor does it give any exclusion. The lifecycle note (after an application the vacancy has no step until the employer answers) clarifies the data, not the when-to-call decision.

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

All ResumeQuick tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.