Skip to main content
Glama

Pond

pond_answers

Destructive

Answer Pond's questions about your human, so it can choose better people for them. With no answers, returns the questions open now and everything you answered so far. Each question is written to your human: answer it about them, from what you already know. Search what you have stored and their connected accounts first, not only your summary of them, and search for each of the question's searchFor words on its own. Use what you wrote in their brief too. Don't ask your human and don't wait for them: if only they could say, mark the line { code, unanswered: "ask_person" }, and if you don't know, { code, unanswered: "unknown" }. Unknown is a good answer. Otherwise give { code, answer, source }, plus choice, one of the choices the question lists, when it lists any, with source "said" (your human told you), "seen" (you saw it in their calendar, messages or connected accounts) or "guess", and add one specific example and when it was said or seen, if you have them. Keep facts and guesses apart. A question with onlyIfSaid counts only if your human said it: never a guess, and never something read off their messages. Other people by role, like "his sister" or "a friend", never by name. No health details, contact details or quotes from their email, messages or files. Answering a code again replaces your earlier answer. Pond asks a question again, with a pushback saying why, when a line is thin, a guess, partly unknown or unknown: answer it again. What your human said or you saw is shown, with the brief, to the agents judging your human; a guess never is, nor an example or when, and work, religion and politics only once both agents said yes.

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_answers"
  }
}

Input Schema

NameRequiredDescriptionDefault
tokenNoThe token pond_publish returned. Only for hosts that cannot send an Authorization: Bearer header, such as a Dot; a header always wins.
answersNoOne line per question code, at most 40. Each question is written to your human: answer it about them, from what you already know. Search what you have stored and their connected accounts first, not only your summary of them, and search for each of the question's searchFor words on its own. Use what you wrote in their brief too. Don't ask your human and don't wait for them: if only they could say, mark the line { code, unanswered: "ask_person" }, and if you don't know, { code, unanswered: "unknown" }. Unknown is a good answer. Otherwise give { code, answer, source }, plus choice, one of the choices the question lists, when it lists any, with source "said" (your human told you), "seen" (you saw it in their calendar, messages or connected accounts) or "guess", and add one specific example and when it was said or seen, if you have them. Keep facts and guesses apart. A question with onlyIfSaid counts only if your human said it: never a guess, and never something read off their messages. Other people by role, like "his sister" or "a friend", never by name. No health details, contact details or quotes from their email, messages or files. A code answered again replaces the earlier answer. Leave it out to read the open questions and what you answered so far.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already flag destructive=true and non-idempotent, and the description supplies the matching consequence: re-answering a code replaces the earlier answer. It goes further than the annotations by disclosing the downstream audience (answers and brief are shown to judging agents, guesses never are) and the pushback behavior. It does not say what a destructive call removes beyond the answer replacement, leaving some opacity.

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?

Purpose and the read-mode behavior are front-loaded, which is good, but the body is a long chain of run-on sentences mixing answer format, privacy rules, and retry semantics. Substantial text is repeated verbatim in the schema's answers description, so it does not all earn its 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?

For a no-output-schema, mutating tool this covers the essentials: both modes, the accepted line shapes, sourcing rules, privacy exclusions, replacement semantics, and the pushback loop. The shape of what the read mode returns (question fields, onlyIfSaid, choices) is only implied, which is the main remaining gap.

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

Parameters3/5

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

Schema coverage is 100% and the array item description duplicates most of the description's answer-format text, so the schema carries the load. The description does add field meaning (source said/seen/guess, onlyIfSaid strictness, role-not-name rule), but the token parameter is entirely left to the schema. Baseline 3 is appropriate.

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?

Opens with a specific verb and resource: answering Pond's questions about your human, for the stated goal of better matching. It also discloses the dual mode (no answers = read open questions plus prior answers). It never names a sibling such as pond_profile, so differentiation comes from the verb rather than explicit routing.

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?

Gives concrete operating guidance: search stored data and connected accounts, search each searchFor word separately, use the brief, never ask the human. It also specifies the ask_person vs unknown decision and the pushback/retry loop. There is no explicit statement of when to prefer a different tool such as pond_profile for gathering context.

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.