Skip to main content
Glama
Sign In

Kosmodrom

by ai.kosmodrom
OverviewDiscussionsAdmin

feature_spec_sync

Read-only

Returns the context for updating a feature's spec from its tasks: feature.spec, tasks[].spec and tasks[].result in one batch plus the workspace's spec-update guidelines (instructions); writes nothing. includeTaskIDs adds full contexts with chats of tasks with discrepancies. mode=analyze - differences and a full new version without saving; mode=apply - when the user asks to apply the update.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mode": "<mode>"
    },
    "name": "feature_spec_sync"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoFeature key #F12; not with featureID
modeYesanalyze - propose without saving; apply - the user asks to apply
basisNoactual (default) - actual state from the tasks; requirements - confirmed in chats
chatLimitNoLatest messages per full context, 1-100; older ones are read from the chat with a before cursor.
featureIDNoFeature ID; not with key
taskTypesNoTask and bug types to include; default frontend, backend, fullstack, design
includeTaskIDsNoTasks with discrepancies to add with full context and chat, up to 20; requires taskTypes, the same as in the previous response

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / taskTypes / items / enum
      Previous value: -[
-  "planning",
-  "analysis",
-  "design",
-  "documentation",
-  "research",
-  "education",
-  "other",
-  "frontend",
-  "backend",
-  "fullstack",
-  "devops",
-  "tests",
-  "freetest",
-  "smoke",
-  "regression",
-  "testcase",
-  "bug_trivial",
-  "bug_minor",
-  "bug_major",
-  "bug_critical",
-  "bug_block"
-]New value: +[
+  "planning",
+  "analysis",
+  "design",
+  "documentation",
+  "research",
+  "education",
+  "marketing",
+  "other",
+  "frontend",
+  "backend",
+  "fullstack",
+  "devops",
+  "tests",
+  "freetest",
+  "smoke",
+  "regression",
+  "testcase",
+  "bug_trivial",
+  "bug_minor",
+  "bug_major",
+  "bug_critical",
+  "bug_block"
+]
  2. Changed4 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / chatLimit / description
      Previous value: -"Latest messages per full context, 1-100; older via chat.before"New value: +"Latest messages per full context, 1-100; older ones are read from the chat with a before cursor."
    • changedInput schema / properties / key / anyOf
      Previous value: -[
-  {
-    "maxLength": 12,
-    "minLength": 1,
-    "type": "string"
-  },
-  {
-    "exclusiveMinimum": 0,
-    "maximum": 9007199254740991,
-    "type": "integer"
-  }
-]New value: +[
+  {
+    "maxLength": 12,
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "exclusiveMinimum": 0,
+    "type": "integer"
+  }
+]
    • changedInput schema / properties / key / description
      Previous value: -"Feature key #F12 (or F12, 12); not with featureID"New value: +"Feature key #F12; not with featureID"
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'writes nothing', which usefully resolves the apparent conflict of an 'apply' mode on a read-only tool. It also explains that includeTaskIDs pulls full contexts with chats for tasks with discrepancies. It doesn't cover pagination/chat-before-cursor behavior, but annotations already carry the safety profile.

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 purpose is front-loaded well, but the remainder is a run-on chain of semicolon-clauses packing mode, includeTaskIDs, and the no-write guarantee into one dense block. Readable but not structured or scannable.

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

Completeness5/5

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

Seven parameters, but the schema is fully self-documenting and there is no output schema, so the description only has to carry purpose, mutation safety, and mode selection — all of which it does. Nothing essential to correct invocation is missing.

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%, so the baseline is 3. The description restates mode and includeTaskIDs semantics that the schema already documents, adding only marginal framing ('tasks with discrepancies') and saying nothing about key/featureID, basis, taskTypes, or chatLimit.

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: returns the batch context (feature.spec, tasks[].spec, tasks[].result plus workspace spec-update guidelines) needed to update a feature's spec. It is distinguishable from the sibling task_spec_sync by operating at the feature level, though it never names that sibling explicitly.

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 a concrete decision rule for the required mode parameter: analyze for differences plus a full new version without saving, apply when the user asks to apply the update. Clear usage context, but no guidance on when to prefer this over feature_context or task_spec_sync.

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

All Kosmodrom toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources