TeamShared

memory_skill_set

Insert a new version of a skill. Each call creates a new version.

Skills are atomic instruction building blocks. Playbooks compose them via tool_recipe.skills on memory_procedure_set. Routed through the guarded ingestion pipeline; only active skills are visible to recall and memory_skill_get.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Skill name (stable id)
`tags`	No	Tags for discovery
`agent`	No	Override agent identity
`body_md`	Yes	Markdown body the agent will read
`owner_id`	No	Org member UUID. Omit inherits last owner or the writer.
`tool_hints`	No	Optional structured hints (preferred MCP tools, params)
`description`	No	One-line summary
`verification_days`	No	Verification window: 30, 90, or 180 days; 0 for none. Omit inherits the last window.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedAug 29, 2026

addedInput schema / properties / owner_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Org member UUID. Omit inherits last owner or the writer."
+}

addedInput schema / properties / verification_days

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Verification window: 30, 90, or 180 days; 0 for none. Omit inherits the last window."
+}

First observedAug 18, 2026

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description carries full behavioral disclosure burden. It discloses that each call creates a new version, routes through a guarded ingestion pipeline, and that only active skills are visible to recall and memory_skill_get. However, it does not describe response behavior, failure conditions, or how a skill becomes active, leaving some important gaps.

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?

The description is three sentences with the primary action front-loaded in the first sentence. The supporting sentences add valuable context about versioning, composition, and visibility without padding or repeating the input schema.

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 an 8-parameter setter with a full output schema, the description covers the key behavioral caveats: every call creates a new version, the write goes through a guarded pipeline, and only active skills are visible. Combined with 100% schema coverage, an agent has enough to invoke the tool correctly, though the practical effects of the 'guarded ingestion pipeline' remain vague.

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 because the input schema already documents every parameter. The description adds conceptual context about skills being atomic building blocks but does not provide parameter-specific meaning beyond what the schema already states.

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?

The description opens with the exact action, 'Insert a new version of a skill,' and reinforces the versioned behavior with 'Each call creates a new version.' This clearly differentiates it from sibling retrieval tools like memory_skill_get, memory_skill_resolve, and memory_skills_list.

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?

The description clearly indicates when to use the tool: to insert a new version of a skill. It also adds usage-relevant context by noting that only active skills are visible to recall and memory_skill_get, implying when a created skill becomes usable. It does not explicitly list alternatives or exclusion cases, but the context is clear for a distinctly named setter.

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

All TeamShared 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.