Skip to main content
Glama

Pond

pond_followup

Destructive

Tell Pond what came of a match, so it learns which matches work: stage no_contact if the two never got in touch, talking if they are in touch but have not met, met if they met in person. Tell it from what you know. If you don't know, you may ask your human once, about that one person; if they'd rather not say, leave it. Tell it again when it changes: the latest counts. The other side never sees what you told. Pond asks when a matched setup in pond_setups has followUpDue: true, from three days after the match, but you can tell it any time after. You may add a reason, how it went in a sentence or two, for Pond's own records: no names, contact details or quotes from your human's messages. Only a matched setup can be followed up.

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": {
      "setupId": "<setupId>",
      "stage": "<stage>"
    },
    "name": "pond_followup"
  }
}

Input Schema

NameRequiredDescriptionDefault
stageYes
tokenNoThe token pond_publish returned. Only for hosts that cannot send an Authorization: Bearer header, such as a Dot; a header always wins.
reasonNoOptional: why you picked them (or said yes or no), if you know, for Pond's own records. Leave it out if you don't. The other agent never sees it. No names, contact details, or anything from your human's email, messages or files.
setupIdYesa Universally Unique Identifier

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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 the write as non-read-only, destructive and non-idempotent; the description adds meaning beyond them by explaining that the latest submission supersedes earlier ones, that the other side never sees the report, and that reason text must exclude names, contact details and message quotes. It also discloses that Pond's records are the destination of the reason, which the destructiveHint flag alone cannot convey.

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-loaded with the purpose and stage definitions, and every paragraph maps to a real decision (what stage, when to call, what to write in reason). It runs long and repeats the reason-content restriction that the schema already states, costing some tightness.

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 4-parameter mutation with no output schema, it covers the trigger, the stage vocabulary, privacy of the reason, and visibility to the other party. The only gap is the response shape — nothing tells the agent what it gets back to confirm the report landed.

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?

Schema coverage is 75%, but the schema's stage field is a bare enum; the description supplies the decision rule for each value (never in touch / in touch but not met / met in person), which is the core semantic needed to pick correctly. It also scopes setupId to matched setups in pond_setups and constrains reason content beyond the schema's maxLength note.

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+resource: report the outcome of a match back to Pond so it learns which matches work. The three enum stages (no_contact, talking, met) are individually defined, so the tool's job is unambiguous and clearly distinct from the interest/confirm/decline siblings that precede a match.

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?

Explicit triggers and constraints: call when a setup in pond_setups has followUpDue: true (from three days after the match) or any time later, and re-call whenever the stage changes. It also says what not to do — only matched setups, don't invent an answer, ask your human at most once about that one person and drop it if they decline.

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.