Skip to main content
Glama

Shipfound

by co.shipfound
OverviewDiscussionsAdmin

The founder's answer to a move

grow_answer

Record yes or no to a move from today or record_action's next, by its key. A no rests the move for 7 days (30 after a second no), so it is not offered again tomorrow. For a yes, from says where the founder found it, so Shipfound learns how often the first five had what they wanted. seen: the moves shown on the next-five screen and not picked, which rest like the first screen's. said: what the founder typed in their own words instead of picking, word for word; Shipfound's ranking reads it as their direction from then on. Free.

Input Schema

NameRequiredDescriptionDefault
keyYesThe move's key
fromNoWhere the move was when the founder picked it: "first" (the first question), "more" (the next five), "all" (the full list), "typed" (they named it in their own words).
saidNoThe founder's own words when they typed an answer instead of picking, as they wrote them.
seenNoKeys of the moves printed on the next-five screen that the founder did not pick.
answerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / from
      Added value: +{
+  "description": "Where the move was when the founder picked it: \"first\" (the first question), \"more\" (the next five), \"all\" (the full list), \"typed\" (they named it in their own words).",
+  "enum": [
+    "first",
+    "more",
+    "all",
+    "typed"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / said
      Added value: +{
+  "description": "The founder's own words when they typed an answer instead of picking, as they wrote them.",
+  "maxLength": 1000,
+  "type": "string"
+}
    • addedInput schema / properties / seen
      Added value: +{
+  "description": "Keys of the moves printed on the next-five screen that the founder did not pick.",
+  "items": {
+    "maxLength": 2000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 10,
+  "type": "array"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations declare non-readOnly and non-destructive, and the description adds real behavioral weight beyond that: a no rests the move 7 days (30 after a second no), `seen` keys also get rested, and `said` becomes ranking input. The cost note ('Free') is a useful side signal. It does not describe the response shape or what a successful recording returns, which keeps it out of the top band.

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 core action is front-loaded, which is right, but the paragraph is dense and interleaves parameter behavior with product behavior in long semicolon-joined clauses. 'which rest like the first screen's' is cryptic and requires re-reading, and the trailing 'Free.' is a fragment. Every clause carries information, but the packaging costs clarity.

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?

There is no output schema, so the description carries the return burden, and it does explain the durable effects (rest windows, ranking learning) rather than the literal response. For a 5-parameter write tool at 80% schema coverage, an agent has enough to invoke it correctly; only the immediate response/confirmation is unstated.

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 a high 80%, so `key` and `from` are already documented; the description nonetheless adds behavioral meaning the schema lacks, notably that `seen` moves rest like the first screen's and that `said` is read as the founder's direction by the ranking. The `answer` enum, the one parameter with no schema description, is covered by the opening sentence ('yes or no').

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 first sentence names the verb (record) and the exact payload (yes/no to a move), and anchors the input source to the `today` and `record_action` siblings by key. That is more specific than the title alone and lets an agent tell it apart from record_action. It stops short of a crisp one-line statement of effect, but the purpose is unambiguous.

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 says when this fires ('a move from today or record_action's next') and spells out the consequence of each answer path, so an agent knows the condition that selects this tool. There is no explicit when-not or named alternative to avoid, so it is a clear context rather than a full routing rule.

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

All Shipfound toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources