Skip to main content
Glama
Sign In

PoliteReach

by com.politereach
OverviewDiscussionsAdmin

Record That They Agreed To A Call

li_track_booking
Destructive

Record that a person AGREED to a call — you read it in their reply ("yes, happy to chat", "Tuesday works, send me a link"). PoliteReach never decides this; you do.

🚨 SEARCH THE CALENDAR FIRST: people often book through the link within minutes of saying yes. If they already booked, do NOT call this — record it with li_mark_booked and send them nothing.

Effect: booking status agreed, bookingAgreedAt stamped, outcome interested (which closes the automated sequence like li_mark_outcome does), and a first check date: the EARLIER of the booking link + the account's firstNudgeHours (48h by default; "now" when the link has not gone out yet) and 09:00 in THEIR timezone on the day BEFORE the day they named — never sooner than 2 hours from now. On that date they appear in li_booking_due.

Pass agreedDayText (their words: "next Tuesday") and, when you can resolve it, agreedDate as "YYYY-MM-DD" in their timezone. Batch with profileUrls. Refused for someone whose call is already booked (cancel it first with li_mark_booking_cancelled). A person in no campaign gets a light record on the account you name.

The booking link itself is detected automatically: any outgoing message containing one of the account's booking links (li_set_booking_settings) stamps it — you never record the link.

Input Schema

NameRequiredDescriptionDefault
noteNoWhy — quote them; stored with the verdict and on the timeline
agreedYesMust be true — this records an agreement, nothing else
contactIdNoOne contact by id (from li_contact_dossier or li_campaign_contacts), instead of profileUrl
messageIdNoThe exact message row, when you already have it from a dossier or a queue read.
sessionIdNoThe account this conversation is on. Only used when the person is in NO campaign: then a light record is created on this account so the mark has something to act on. Needed only when you have more than one account.
agreedDateNoThe calendar day those words mean, "YYYY-MM-DD", resolved by you in THEIR timezone. Omit when they named no day.
campaignIdNoWhich campaign membership to act on. A contact can be in more than one campaign, and without this the row is whichever was touched last — so stopping them in one campaign while leaving the other running was not possible. Pass it whenever the contact might be in two.
profileUrlNoOne contact, by profile URL
profileUrlsNoSeveral contacts in ONE call, max 200. Each is resolved and marked independently: one refusal does not stop the rest, and the reply reports every one by URL.
sessionLabelNoSame, by account label
agreedDayTextNoTheir own words for when, e.g. "next Tuesday afternoon"
conversationUrnNoThe thread, straight from li_list_conversations (single-person form). Recorded on the conversation so the live inbox recognises it as decided. On its own it finds the person only when their thread is already stored — pass profileUrl (the participantProfileId / ACoAA… URL) too.
participantNameNoTheir name from li_list_conversations — kept on a newly recorded contact.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / contactId / description
      Added value: +"One contact by id (from li_contact_dossier or li_campaign_contacts), instead of profileUrl"
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations (which only give readOnly/destructive/openWorld hints): it discloses the exact side effects (status `agreed`, `bookingAgreedAt` stamped, outcome `interested` closing the sequence), the first-check-date computation, refusal conditions for already-booked contacts, batch independence, and the light-record fallback for non-campaign people. This is unusually rich behavioral disclosure.

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 and the critical 'search the calendar first' warning, then orders effects, timing, and parameters sensibly. It is dense and long, but for a 13-parameter mutation with intricate timing logic most sentences earn their place.

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?

Covers effects, timing, refusals, batching, and edge cases thoroughly for a complex mutating tool. The only minor gap is that with no output schema the description says little about the reply shape beyond 'reports every one by URL'.

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 cross-parameter meaning the schema states only in isolation: the agreedDayText/agreedDate pairing, batching via profileUrls, and the sessionId-only-when-no-campaign rule. It also clarifies that the booking link is auto-detected and never passed as a parameter.

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 and resource ('Record that a person AGREED to a call') and explicitly disambiguates from the near-identical sibling li_mark_booked ('If they already booked, do NOT call this'). An agent can route between the two without opening either 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?

Gives the trigger condition ('you read it in their reply'), an explicit exclusion ('If they already booked, do NOT call this'), and names the alternative to use instead (li_mark_booked, li_mark_booking_cancelled). When/when-not and alternatives are all present.

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