Skip to main content
Glama
Sign In

PoliteReach

by com.politereach
OverviewDiscussionsAdmin

Withdraw Pending Sent Invitations

li_withdraw_invites
Destructive

Withdraw connection invites this account has sent that are still pending. Give profileUrls for specific people, and/or olderThanDays to retire everything past that age. Reads LinkedIn's OWN pending list, so it also covers invites sent outside this system (manual/Airtable-era outreach) — not just ones in the database. Stale ignored invites drag the acceptance rate LinkedIn judges the account on. NOTE: LinkedIn blocks re-inviting the same person for ~3 weeks after a withdrawal. State-changing — requires confirmWithdraw=true. Draws from the account's ONE shared daily withdrawal allowance (autoWithdrawPerDay), the same one the automatic sweep spends, so asking for more than is left today is not an error: it withdraws what remains and the reply's note says how many days the rest will take. Report that ETA to the user rather than implying everything was withdrawn.

Input Schema

NameRequiredDescriptionDefault
waitNoBlock until the run finishes. Default false — a backlog drain takes minutes; read li_withdraw_status instead.
sessionIdNoAccount id from li_list_accounts. Needed (or sessionLabel) when you have more than one account; never guessed.
maxWithdrawNoCeiling for one run (default 25). The shared daily allowance still applies and may be lower.
profileUrlsNoWithdraw these specific profile URLs.
sessionLabelNoAccount by label, LinkedIn name, profile slug or member id (li_list_accounts). Needed (or sessionId) when you have more than one account; never guessed.
olderThanDaysNoWithdraw every pending invite at least this many days old (e.g. 30).
confirmWithdrawYesMust be true to withdraw; false returns a dry-run preview

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / sessionId / description
      Added value: +"Account id from li_list_accounts. Needed (or sessionLabel) when you have more than one account; never guessed."
    • addedInput schema / properties / sessionLabel / description
      Added value: +"Account by label, LinkedIn name, profile slug or member id (li_list_accounts). Needed (or sessionId) when you have more than one account; never guessed."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructive/openWorld, but the description adds substantial non-obvious behavior: the ~3-week re-invite cooldown LinkedIn enforces, the confirmWithdraw=true gate, the shared daily allowance (autoWithdrawPerDay) that the automatic sweep also spends, that over-requesting is not an error, and that the reply's note carries the multi-day ETA the agent must surface.

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?

Purpose is front-loaded and the sentences are information-dense, but the passage is long and the acceptance-rate motivation plus the ETA-reporting instruction add length. Nearly every sentence earns its place, though the density works against quick scanning.

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?

For a state-changing tool with no output schema, the description covers what an agent needs: prerequisites, targeting options, allowance interaction, partial-success behavior, and the fact that a `note` field in the reply carries the ETA. Nothing critical to correct invocation is missing.

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 baseline is 3, but the description adds real meaning beyond the schema: it clarifies that profileUrls and olderThanDays can be combined, and that maxWithdraw is capped by the shared daily allowance rather than a per-run setting. It doesn't restate confirmWithdraw's dry-run semantics, which the schema already carries.

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 (withdraw) and resource (connection invites this account has sent that are still pending), and its scope is clearly delineated against li_pending_invites (list) and li_set_auto_withdraw (configure). The agent can identify the operation without opening the schema.

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?

Explains the two targeting modes explicitly (profileUrls for specific people, and/or olderThanDays for age-based retirement) and routes status polling to li_withdraw_status rather than the blocking wait. It also distinguishes manual withdrawals from the automatic sweep, so the agent knows how this fits alongside the scheduled behavior.

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

All PoliteReach toolsInspect
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