Skip to main content
Glama

Shipfound

by co.shipfound.api
OverviewDiscussionsAdmin

Today

today

What /shipfound:grow shows: what happened since the founder's last session (AI visits, AI crawler hits, conversions, what got verified or failed), what is due (tests with a verdict, shipped work to verify), the one move to offer, the next two (after), every other move with work behind it (more), and every other kind of move Shipfound makes (catalog, with ready false and what it needs when something comes first), so a founder can reach any of it. focus is what holds the product back this week, read from its numbers, and the three choices go after it. Each move's why is the reason to do it for this product today, chosen and written over the founder's own results, the people who asked, the peer study and the play library (what it does is in does when why is that reason); gets is who it reaches and the first sign to watch for; then is what it leads to once its own work is done; rests is what it rests on in one line. It looks first, from stored data: a move is offered only when there is concrete work behind it (checks still failing on the live site, directories not listed yet, the page worth writing with its volume), and not the same move two days running. Logs the offer. Free.

Input Schema

NameRequiredDescriptionDefault
featuresNoFeatures the founder shipped in the last 14 days, read from the repo (merged PRs, feat: commits), leaving out Shipfound's own PRs: what each does for the person using the product, the problem it solves when the code or PR says, and the PR link. Lets today offer a post or an X Article about one.
repoCommitsNoCommits to the founder's product in the last 7 days, read from their repo, leaving out Shipfound's own PRs (branches named shipfound/...). Lets today offer a build in public note on the week's work. Leave out when there is no repo.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / features
      Added value: +{
+  "description": "Features the founder shipped in the last 14 days, read from the repo (merged PRs, feat: commits), leaving out Shipfound's own PRs: what each does for the person using the product, the problem it solves when the code or PR says, and the PR link. Lets today offer a post or an X Article about one.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "problem": {
+        "maxLength": 300,
+        "type": "string"
+      },
+      "title": {
+        "maxLength": 160,
+        "minLength": 3,
+        "type": "string"
+      },
+      "url": {
+        "maxLength": 500,
+        "type": "string"
+      }
+    },
+    "required": [
+      "title"
+    ],
+    "type": "object"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
  2. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / repoCommits
      Added value: +{
+  "description": "Commits to the founder's product in the last 7 days, read from their repo, leaving out Shipfound's own PRs (branches named shipfound/...). Lets today offer a build in public note on the week's work. Leave out when there is no repo.",
+  "maximum": 100000,
+  "minimum": 0,
+  "type": "integer"
+}
  3. Added

TDQS

C2.4/5.0
Behavior3/5

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

The description usefully explains the non-readOnly annotation: "Logs the offer" clarifies that calling it has a write side effect, and it discloses that selection is data-driven and de-duplicated across days. That said, the behavior is buried in jargon, and there is no mention of cost, latency, or what a caller gets back at the top level. No contradiction with annotations.

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

Conciseness2/5

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

Roughly 200 words delivered as one sprawling run-on sentence with nested parentheticals, and it is not front-loaded: the reader gets a list of outputs before learning what the tool is. Substantial length is spent on undefined internal terminology rather than decision-relevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does carry the burden of describing return content, and it attempts this thoroughly (what's due, the offer, the next two, the catalog, plus per-move fields). However, the field names used ("why", "gets", "then", "rests") are opaque enough that an agent cannot reliably consume the structure, so the coverage is nominal rather than usable.

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 description coverage is 100% and both parameters (`features`, `repoCommits`) carry detailed, self-sufficient descriptions including filtering rules and omission guidance. The prose never references either parameter, so it adds nothing beyond the schema — the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with "What /shipfound:grow shows" and then enumerates output sections in private vocabulary ("the one move", "every other move", "catalog", "rests", "gets") without ever stating the plain action, e.g. "returns today's growth briefing for a product." An agent must reverse-engineer the verb from a list of unknown nouns, and it is not distinguishable from siblings like `plan`, `grow_answer`, or `ideas` on the evidence given.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this instead of `plan`, `grow_answer`, `ideas`, or `shipped`. The only conditional sentences ("a move is offered only when there is concrete work behind it", "not the same move two days running") describe the tool's internal selection logic, not caller guidance.

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