Reach MCP — LinkedIn for AI agents

update_account_quotas

Idempotent

Update one or more quota configuration fields for a LinkedIn account, and its activity window (the hours, days and timezone jobs run in when a job does not set its own). Only provided fields are updated. Changes limits and the activity window for jobs; does not reset today's counters. Raising a limit is the user's decision, ask first.

Input Schema

TableJSON Schema

Name	Required	Description
`timezone`	No	IANA zone for the window, e.g. Europe/Paris. Empty string resets to the zone of the account's proxy country.
`account_id`	Yes	Reach id of the LinkedIn account to act on, from list_accounts.
`window_end`	No	HH:MM: jobs on this account stop at this time. Empty string resets to 18:00.
`window_days`	No	Weekdays jobs may run: mon, tue, wed, thu, fri, sat, sun. Empty list resets to Monday–Friday.
`window_start`	No	HH:MM, in the account's timezone: jobs on this account start no earlier. Empty string resets to 09:00.
`idempotency_key`	No	Optional. A key you choose (a UUID is fine) that names this exact call. If you retry with the same key and the same arguments, the first call's result is returned and nothing is done twice on LinkedIn. Reusing a key with different arguments is refused. Keys expire after 24 hours.
`daily_posts_conf`	No	Daily limit for 'posts' on this account; 0 means unlimited.
`daily_visits_conf`	No	Daily limit for 'visits' on this account; 0 means unlimited.
`daily_comments_conf`	No	Daily limit for 'comments' on this account; 0 means unlimited.
`daily_messages_conf`	No	Daily limit for 'messages' on this account; 0 means unlimited.
`daily_reactions_conf`	No	Daily limit for 'reactions' on this account; 0 means unlimited.
`daily_invitations_conf`	No	Daily limit for 'invitations' on this account; 0 means unlimited.
`daily_job_searches_conf`	No	Pages of search_job_postings (up to 25 postings each) per UTC day. Default 50; 0 = not limited.
`daily_messaging_reads_conf`	No	Inbox reads (conversations, messages, Sales Navigator threads) per UTC day. Default 300; 0 = not limited.
`daily_imports_salesnav_conf`	No	Daily limit for 'imports_salesnav' on this account; 0 means unlimited.
`daily_imports_standard_conf`	No	Daily limit for 'imports_standard' on this account; 0 means unlimited.
`daily_imports_recruiter_conf`	No	Daily limit for 'imports_recruiter' on this account; 0 means unlimited.
`daily_linkedin_requests_conf`	No	Ceiling on all LinkedIn requests (reads included) per UTC day; protects the account from a LinkedIn restriction. 1 to 2000, default 1000. Raising it is the user's decision.
`messaging_min_interval_seconds`	No	Seconds before the same inbox page or conversation can be read again. Default 60; 0 = off.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`quotas`	No
`window`	No
`updated`	No
`account_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 8, 2026

addedInput schema / properties / daily_job_searches_conf

Added value: +{
+  "description": "Pages of search_job_postings (up to 25 postings each) per UTC day. Default 50; 0 = not limited.",
+  "minimum": 0,
+  "type": "integer"
+}

Changed3 schema fields changedOct 8, 2026

addedInput schema / properties / daily_linkedin_requests_conf

Added value: +{
+  "description": "Ceiling on all LinkedIn requests (reads included) per UTC day; protects the account from a LinkedIn restriction. 1 to 2000, default 1000. Raising it is the user's decision.",
+  "maximum": 2000,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / daily_messaging_reads_conf

Added value: +{
+  "description": "Inbox reads (conversations, messages, Sales Navigator threads) per UTC day. Default 300; 0 = not limited.",
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / messaging_min_interval_seconds

Added value: +{
+  "description": "Seconds before the same inbox page or conversation can be read again. Default 60; 0 = off.",
+  "minimum": 0,
+  "type": "integer"
+}

Changed5 schema fields changedSep 27, 2026

addedInput schema / properties / timezone

Added value: +{
+  "description": "IANA zone for the window, e.g. Europe/Paris. Empty string resets to the zone of the account's proxy country.",
+  "type": "string"
+}

addedInput schema / properties / window_days

Added value: +{
+  "description": "Weekdays jobs may run: mon, tue, wed, thu, fri, sat, sun. Empty list resets to Monday–Friday.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / window_end

Added value: +{
+  "description": "HH:MM: jobs on this account stop at this time. Empty string resets to 18:00.",
+  "type": "string"
+}

addedInput schema / properties / window_start

Added value: +{
+  "description": "HH:MM, in the account's timezone: jobs on this account start no earlier. Empty string resets to 09:00.",
+  "type": "string"
+}

addedOutput schema / properties / window

Added value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedSep 10, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover safety and idempotency (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the description's added value is real context: partial-merge semantics, the fact that today's counters survive, and the requirement to confirm limit increases with the user. It does not describe what a response contains beyond the output schema, which is acceptable.

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?

Three compact sentences, front-loaded with the verb and resource, and the parenthetical explaining the activity window is well placed. Slight redundancy between 'Changes limits and the activity window for jobs' and the opening sentence, but nothing gratuitous.

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 19-parameter mutation with a full schema, complete annotations, and an output schema, the description covers the important non-schema facts: merge semantics, non-reset of counters, and the user-consent rule. Minor gaps remain around cross-field constraints (e.g. window_start vs window_end) and error behavior, which are not fatal.

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 3 baseline applies, but the description adds non-schema semantics: updates are a merge of only-supplied fields, and the timezone/window_start/window_end/window_days parameters form one coherent 'activity window' concept. That is genuine added meaning over the per-field prose.

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?

Names a specific verb (update) and resource (quota configuration fields plus the account's activity window) and scopes the change to one LinkedIn account. It is clearly distinguishable from the read sibling get_account_quotas and from unrelated update_* tools.

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?

States the operative condition ('Only provided fields are updated'), the effect domain ('changes limits and the activity window for jobs'), a key exclusion ('does not reset today's counters'), and a decision gate ('Raising a limit is the user's decision, ask first'). It stops short of pointing to get_account_quotas for inspection of current values, so routing between read and write is left to inference.

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

All Reach MCP — LinkedIn for AI agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?