Skip to main content
Glama
bzdOS

hubd

by bzdOS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

hub_card_set

Create or update a project card from just a name and digest, no folder or git checkout needed. Patch one stale line with replace or appendLine instead of rewriting the whole digest.

Instructions

Create or update a project card from just a name and a digest — no folder needed (unlike hub_sync). Use it to capture a project that is not a local git checkout, e.g. when harvesting a dialog. Preserves any hand-written frontmatter and Facts. To fix ONE stale line without touching the owner's framing, patch instead of replacing: replace: [{from, to}] and/or appendLine — a from that is not in the digest is an error, not a silent no-op.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
byYesthe function you are performing, e.g. "dev-hubd". NOT which model you are — that is read from the transcript, and many sessions share a model. NOT a queue role either: a role is a mailbox (see hub_queue_wait), this is who is at it.
digestNothe card digest: 3-6 lines of current state (replaces the whole text — omit it when patching)
projectYesproject name or slug
replaceNopatch: exact substrings to swap, each must occur exactly once in the current digest
appendLineNopatch: one line to add at the end of the current digest

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.9.15
    • addedInput schema / properties / appendLine
      Added value: +{
+  "description": "patch: one line to add at the end of the current digest",
+  "type": "string"
+}
    • changedInput schema / properties / digest / description
      Previous value: -"the card digest: 3-6 lines of current state"New value: +"the card digest: 3-6 lines of current state (replaces the whole text — omit it when patching)"
    • addedInput schema / properties / replace
      Added value: +{
+  "description": "patch: exact substrings to swap, each must occur exactly once in the current digest",
+  "items": {
+    "properties": {
+      "from": {
+        "type": "string"
+      },
+      "to": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "from",
+      "to"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedInput schema / required
      Previous value: -[
-  "project",
-  "digest",
-  "by"
-]New value: +[
+  "project",
+  "by"
+]
  2. Changed2 schema fields changedv0.5.0
    • changedInput schema / properties / by / description
      Previous value: -"who is writing"New value: +"the function you are performing, e.g. \"dev-hubd\". NOT which model you are — that is read from the transcript, and many sessions share a model. NOT a queue role either: a role is a mailbox (see hub_queue_wait), this is who is at it."
    • changedInput schema / required
      Previous value: -[
-  "project",
-  "digest"
-]New value: +[
+  "project",
+  "digest",
+  "by"
+]
  3. First observedv0.1.6

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that existing hand-written frontmatter and Facts are preserved, that 'digest' replaces the entire text, and — crucially — that a 'from' not present in the digest is an error rather than a silent no-op. It does not cover permissions/auth or create-vs-update conflict behavior, so it is not fully exhaustive.

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?

Four tight sentences, front-loaded with the core action, then usage, then preservation guarantees, then patch mechanics. No filler; each sentence contributes distinct information (what, when, side effects, patch semantics).

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 5-parameter mutation tool with no annotations and no output schema, the description covers purpose, alternatives, preservation, patch modes, and error semantics well. It omits return/confirmation format and any permission requirements, which leaves a minor gap but not one that would cause a mis-call.

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 100%, so the baseline is 3; the description nonetheless adds real semantics beyond the schema: 'digest' fully replaces the text and should be omitted when patching, and unmet 'from' targets raise an error (the schema only says each must occur exactly once). These clarifications justify going above baseline.

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?

Starts with a specific verb+resource ('Create or update a project card') and immediately scopes it ('from just a name and a digest — no folder needed'), explicitly contrasting with the sibling hub_sync. It also distinguishes the two operating modes (replace vs patch), so an agent can identify the tool and its scope without opening the schema.

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?

Gives explicit when-to-use ('capture a project that is not a local git checkout, e.g. when harvesting a dialog') and an explicit alternative ('unlike hub_sync'). It further routes intra-tool behavior: use patch ('replace'/'appendLine') rather than a full replace to fix one stale line without disturbing the owner's framing.

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

Deploy Server

Other Tools