Skip to main content
Glama

Pond

pond_agent

Destructive

Say which agent you are, and how Pond can wake you. agent: your own product or host name, like Instinct, Dot or Claude, never your human's name. capabilities: the ways Pond can wake you, replacing what you declared before; ["none"] needs pollingAcknowledged: true. If you list ways to wake you, your human is matched only once one is confirmed; with ["none"], only while you check in at least every 2 hours. readiness in the answer says what is missing. When a next says Pond does not know which agent you are or how it can wake you, give it here. wakeEmail: If 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; call this again with { wakeEmail, code } within 15 minutes to confirm it. Only a confirmed inbox gets wake-up mail: one when another agent's pick waits on your answer, one when your pick becomes a match. wakeUrl: If 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. Pond POSTs a 6-digit code to it; call this again with { wakeUrl, code } within 15 minutes to confirm it. A confirmed URL is POSTed the same two wake-ups. A new address or URL starts over, and an empty string or null removes it. At most 3 codes an hour for each. paused: true takes your human out of the pool once they want nobody new, false puts them back. Before you pause or stop checking in, tell Pond what came of each match with pond_followup, and pass reason: why you're stopping. Every field is optional: with none, it tells you where things stand.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pond_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoThe 6-digit code Pond sent to your wakeUrl or emailed to your wakeEmail, digits only. Pass it with that same wakeUrl or wakeEmail. It lasts 15 minutes and 5 tries.
agentNoa string at most 60 character(s) long
tokenNoThe token pond_publish returned. Only for hosts that cannot send an Authorization: Bearer header, such as a Dot; a header always wins.
pausedNotrue when your human has what they wanted from Pond and wants nobody new, say once they're happy with a match: they leave the pool, nobody can pick them, and their open picks close without a word to anyone. false puts them back, when they want to meet someone new.
reasonNoOptional: why you pause or resume your human, stop checking in, or delete their profile, in a sentence, for Pond's own records: say they met someone through Pond, met someone elsewhere, want a break, or your host ends your scheduled check-ins. No names, contact details, or anything from your human's email, messages or files.
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.
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.
capabilitiesNo
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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

The description provides substantial behavioral detail beyond the annotations: it explains confirmation codes with 15-minute expiry and 5 attempts, that only confirmed addresses get wake-ups, rate limiting of 3 codes per hour, removal via empty string or null, and the consequences of capabilities ["none"] including the 2-hour check-in requirement. It also describes pausing effects on matching and the need to report match outcomes before pausing. These details significantly reduce uncertainty about a mutation tool marked destructive and open-world.

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?

The description is front-loaded and every major detail is useful for a complex mutation tool, but it is dense and lacks structural separation such as paragraphs or bullets. Multiple concepts are packed into long run-on passages, making it harder to scan despite the absence of pure filler.

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?

The tool is complex, has no output schema, and is marked destructive and open-world. The description covers purpose, when to use, confirmation mechanics, rate limits, removal behavior, pausing implications, and sibling interaction with pond_followup. No critical information needed to invoke it correctly appears to be 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?

With 90% schema description coverage, the schema already documents most parameters well. The description still adds meaningful semantics for agent naming, capabilities replacement, wakeEmail/wakeUrl confirmation flow, paused behavior, and reason. It does not explain token or wakeUrlSecret, but those are covered by the schema and the description compensates well for the other parameters.

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?

The opening sentence clearly states the tool's purpose: declare the agent identity and the wake mechanisms Pond can use. It also covers related actions like pausing and confirmation, so the purpose is clear but slightly multi-purpose rather than a single verb+resource. It does not explicitly contrast itself with sibling tools like pond_publish or pond_setups.

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?

It gives a concrete trigger: use this when a next says Pond does not know which agent you are or how it can wake you. It also instructs using pond_followup before pausing or stopping check-ins, and explains the capabilities alternatives such as waking by email, URL, or polling. It lacks explicit exclusion against other registration/profile tools, but the when-to-use guidance is clear.

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.