Skip to main content
Glama

Knowledge skills

knowledge_skills
Read-onlyIdempotent

Reads the workspace's methods (skills) and documents for specialist work. command with a known route key (budget-pacing, unit-economics, revenue-reconciliation, market-test and others) returns a method's full body in one call; query searches, and a returned skillId or documentId reads one entry. Strategic proposals, read-only plans and requests not to launch each have a method. Lists return metadata with nextOffset. Workspace scope and approvals apply.

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": {
      "input": "<input>"
    },
    "name": "knowledge_skills"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes
accountIdsNoOptional account selection; can only narrow this workspace's access.
userStatementNoRequired for launch_brief: the user's request or answer for this launch, in their own words. Otherwise optional: the user's request for this call, treated as an unverified user statement, never permission or verified platform evidence.
idempotencyKeyNoRequired for mutations. Reuse the same key only when retrying the exact same call; a completed outcome is applied once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / input / properties / documentId
      Added value: +{
      +  "maxLength": 40,
      +  "type": "string"
      +}
    • changedInput schema / properties / input / properties / offset / description
      Previous value: -"Continue discovery using the previous nextOffset and the same query; ignored for a skillId read."New value: +"Previous nextOffset."
    • changedInput schema / properties / userStatement / description
      Previous value: -"Required for launch_brief: the latest verbatim user request or free-text answer. Otherwise optional user-provided context, treated as an unverified user statement, never permission or verified platform evidence."New value: +"Required for launch_brief: the user's request or answer for this launch, in their own words. Otherwise optional: the user's request for this call, treated as an unverified user statement, never permission or verified platform evidence."
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds behavior beyond that: lists return metadata with nextOffset (a pagination contract), a known command key returns the full body in a single call, and workspace scope plus approvals constrain what is returned.

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

Conciseness4/5

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

The two-mode reading path is front-loaded in the opening sentence and every clause carries information; there is no filler. The second sentence is long and semicolon-chained, and phrases like 'route key' sit awkwardly next to the 'command' parameter name, costing some immediate readability.

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 nested, 4-parameter read tool with no output schema, the description covers the main decision paths, the pagination token and the permission boundary. Gaps remain around empty-input behavior (does an empty input list everything?) and the roles of accountIds and userStatement, but nothing critical to a correct call is absent.

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 75%, so several parameters are already documented, but the description adds the interaction logic the schema does not: query searches and yields skillId/documentId values, which are then used to read a single entry, while command resolves a known route key directly. It does not mention accountIds, userStatement or idempotencyKey, which are left entirely to the schema.

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 description names a specific verb and resource set: reading the workspace's methods (skills) and documents for specialist work, and enumerates the access modes (command, query, skillId, documentId). It is distinguishable from knowledge_propose by being explicitly a read path, but it never names that sibling or any other, so the differentiation is implicit rather than stated.

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 gives clear routing context for each mode: use command with a known route key to get a method's full body in one call, use query to search, use a returned skillId or documentId to read one entry. It also signals the domain ('Strategic proposals, read-only plans and requests not to launch each have a method'). What is missing is any explicit exclusion or pointer to alternatives such as knowledge_propose or workflows_list.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.