Geode

Surveys: make a new survey 5

geode_surveys_make_a_new_survey_5

Create a 5-question survey that pays each respondent payout. value must be at least payout × max_responses (the survey's budget). Writes to the chain: this prepares an unsigned transaction (an intent) for signer; nothing happens until you sign it with geode-local-signer and submit it with geode_submit_intent.

Input Schema

TableJSON Schema

Name	Required	Description
`value`	Yes	GEODE to send with this call (explicit; never inferred)
`payout`	Yes	Amount in GEODE as a decimal string (e.g. "1.25"), or {"raw": "<planck>"}
`public`	Yes
`signer`	Yes	Your account address (SS58). The transaction is prepared for this account; you sign it on your own machine with geode-local-signer.
`question_1`	Yes	UTF-8 text, at most 512 bytes; no control or invisible characters
`question_2`	Yes	UTF-8 text, at most 512 bytes; no control or invisible characters
`question_3`	Yes	UTF-8 text, at most 512 bytes; no control or invisible characters
`question_4`	Yes	UTF-8 text, at most 512 bytes; no control or invisible characters
`question_5`	Yes	UTF-8 text, at most 512 bytes; no control or invisible characters
`survey_name`	Yes	UTF-8 text, at most 512 bytes; no control or invisible characters
`confirm_token`	No	Token from the first call, to confirm this irreversible action
`max_responses`	Yes	Non-negative integer as a string of digits

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 17, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorld=true), and the description adds genuinely non-obvious behavior: the write is deferred to a sign-and-submit flow and the survey budget must satisfy value >= payout × max_responses. It omits any mention of the confirmation step, which is a real gap for an irreversible action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no padding, with the budget constraint and the deferred-write warning front-loaded where the agent will read them before assembling arguments.

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 12-parameter mutation with no output schema, the description covers the critical execution model (intent, not a committed write) but never mentions the confirm_token confirmation phase implied by the schema, leaving an agent to infer that a second call exists.

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 already 92%, so the baseline is 3, but the description adds a relational constraint between `value`, `payout`, and `max_responses` that appears in no schema field. `public` and `confirm_token` remain unexplained beyond their schema text.

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 ('Create a 5-question survey') and immediately differentiates itself from the sibling survey-creation variants (make_a_new_survey_1/_3) via the question count. An agent can pick the right variant without opening any schema.

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?

Explicitly states the sequence that must follow: the call only prepares an unsigned intent for `signer`, and nothing happens until it is signed locally and submitted via geode_submit_intent. It does not spell out when to choose this over the 1- or 3-question siblings beyond the implied count, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Geode tools Inspect

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

Need Help?