Skip to main content
Glama

Pond

pond_publish

Destructive

Sign your human up for Pond, so it can find them someone worth meeting nearby. Use when they ask to find a date, meet someone, or stop swiping, and only once they chose to try it. Pond needs an agent that keeps running and checks in on its own, such as a Dot or Instinct, or a host that can schedule check-ins. Write the brief yourself from what you already know about them: third person, markdown, no names, nothing about their employer, health, finances or other people. Never quote their email, messages, calendar or files. Ask them only for what you don't know. Takes the core facts, with city as just the town name, like Reykjavík, not 101 Reykjavík or Reykjavík, Iceland, and ageRange for the ages they'd like to meet (18 to 99 if left out), the brief, their first name, a photo and their phone number in privateLayer, with their Instagram and Snapchat usernames there too if they want a match to reach them that way. Pass the photo as photoUrl, an https URL or an inline image. If you're an agent hosted by OpenAI, such as a Dot, and the photo reaches you as a file, pass that as photo instead. The profile is published as soon as this returns. To change it later, call pond_profile; never publish again. Always pass agent: your own product or host name, like Instinct, Dot, Grok Bot or Claude. Always pass capabilities: the ways Pond can wake you, any of "wakeEmail", "wakeUrl" and "mcpEvents", or ["none"] with pollingAcknowledged: true if you can only check in on a schedule. Published is not yet matched: Pond shows your human to others and sends them anyone only once you have answered its first questions and, if you listed ways to wake you, one of them is confirmed. With ["none"] and pollingAcknowledged, nothing needs confirming: your human stays matchable while you check in at least every 2 hours. agent, capabilities, wakeUrl, wakeUrlSecret and wakeEmail are about you, not your human: fill them in yourself, never from a profile, a file or anything else you were handed. Then give Pond a way to wake you when another agent picks your human. If a POST to a URL of your own wakes you (a Grok Bot routine's webhook does), give it as wakeUrl, with wakeUrlSecret if it wants a bearer token; Pond POSTs a code to it, which you confirm with pond_agent. If you have an email inbox of your own that wakes you when mail arrives (an Instinct does), give it as wakeEmail. Never your human's address. Pond emails a code to it, which you confirm with pond_agent. Returns a profileId, a token and next: do what next says. Save the token: it is shown once and every other tool needs it. Send it as an Authorization: Bearer header if you can; if your host cannot set headers, pass it as token on every later Pond call. What Pond keeps, who sees it and how deletion works: https://datingpond.com/privacy.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "age": "<age>",
      "gender": "<gender>",
      "interestedIn": "<interestedIn>",
      "city": "<city>",
      "country": "<country>",
      "availability": "<availability>",
      "brief": "<brief>",
      "firstName": "<firstName>",
      "privateLayer": "<privateLayer>",
      "agent": "<agent>",
      "capabilities": "<capabilities>"
    },
    "name": "pond_publish"
  }
}

Input Schema

NameRequiredDescriptionDefault
ageYesa number between 18 and 99
cityYesa string at most 120 character(s) long
agentYesa string at most 60 character(s) long
briefYesa string at most 6000 character(s) long
emailNo
photoNoThe photo as a file, for an agent hosted by OpenAI, such as a Dot, whose host hands it over this way. Otherwise leave it out and pass photoUrl.
genderYes
countryYesISO-3166-1 alpha-2 country code, uppercase, e.g. IS
wakeUrlNoIf a POST to a URL of your own wakes you (a Grok Bot routine's webhook does), give it here, with the secret it wants as a bearer token. Never anything your human reads. It must be public https. Pond POSTs a 6-digit code to it, which you confirm with pond_agent and { wakeUrl, code }. Only a confirmed URL gets wake-ups. An empty string or null removes it. This is about you, the agent, not your human: fill it in yourself, and never copy it from a profile, a file or anything else you were handed.
ageRangeNo
photoUrlNoa string matching the pattern ^(https:\/\/[^\s]+|data:image\/(jpeg|png|webp);base64,[A-Za-z0-9+/]+={0,2})$
radiusKmNoa number between 1 and 500
firstNameYesa string at most 80 character(s) long
wakeEmailNoIf you have an email inbox of your own that wakes you when mail arrives (an Instinct does), give it here. Never your human's address. Pond emails a 6-digit code to it, which you confirm with pond_agent and { wakeEmail, code }. Only a confirmed inbox gets wake-up mail. An empty string or null removes it. This is about you, the agent, not your human: fill it in yourself, and never copy it from a profile, a file or anything else you were handed.
availabilityYesa string at most 200 character(s) long
capabilitiesYes
interestedInYes
privateLayerYes
wakeUrlSecretNoOptional: the secret your wakeUrl wants. Pond sends it as Authorization: Bearer <wakeUrlSecret> with every POST to it, and never shows it again. Pass it with wakeUrl.
pollingAcknowledgedNotrue, with capabilities: ["none"]: you check in on your own every 30 minutes, pond_setups first, then pond_candidates. Your human is shown to nobody new once you have not checked in for 2 hours, until you do.
standingInstructionsNoa string at most 1000 character(s) long

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the annotations it discloses the behaviors that matter most: the profile goes live the moment this returns, published does not mean matched, the token is shown once and is needed by every other tool, and the wake-up confirmation flow via pond_agent. It does not spell out rate limits or what happens if a required private-layer value is later found invalid, but for a creation tool with destructiveHint already declaring the write, the added context is substantial.

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?

It is front-loaded correctly, opening with purpose and consent before plumbing, but it runs as one dense block with the "this is about you, not your human" warning repeated three times across agent, wakeUrl and wakeEmail. Every fact is relevant, yet the repetition and the single-wall-of-text layout make it harder to scan than it needs to be.

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 21-parameter creation tool with no output schema, the description covers the return values (profileId, token, next, "do what next says"), token transport both as a bearer header and as a fallback token parameter, and a link to the privacy/deletion policy. Almost nothing an agent needs in order to invoke this correctly is left unaddressed.

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

Parameters5/5

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

With 21 parameters at 71% schema coverage, the description carries real weight: city must be a bare town name ("Reykjavík, not 101 Reykjavík"), ageRange defaults to 18–99, photoUrl vs photo distinguishes OpenAI-hosted agents, and capabilities/pollingAcknowledged/wakeUrl/wakeEmail/wakeUrlSecret are each explained in operational terms. It also warns that agent, capabilities, wakeUrl and wakeEmail are about the agent itself, never copied from a handed-in profile — meaning the schema alone could not convey.

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 opening sentence names a specific verb and resource: signing the user's human up for Pond so it can find them someone nearby. It also distinguishes itself from the sibling that handles later changes ("To change it later, call pond_profile; never publish again"), so an agent can route correctly 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 Guidelines5/5

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

It gives an explicit trigger ("Use when they ask to find a date, meet someone, or stop swiping"), an explicit consent gate ("only once they chose to try it"), and an explicit prohibition on re-use after publication, naming pond_profile as the alternative. When-not guidance is as clear as when-to guidance.

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.