Skip to main content
Glama

freedom-mcp

by com.getfreedomos

update_agent_skill

Create or update a skill (process/procedure) for an agent. Use when a user says "@Marcus here's how I want you to do the cash forecast" or "change how the CFO does the monthly review" or "here's my process for X". Skills teach agents HOW to perform their activities.

[sensitive-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stepsYesOrdered steps of the process (e.g., ["Pull balances", "Calculate 13-week average", "Flag if runway < 3 months"])
agent_idNoUUID of the agent to teach. Optional if agent_name is provided.
companyIdYesFreedomOS company id to act within (you must be a member). Required for company-scoped tools.
resourcesNoURLs, doc names, templates, or other resources (e.g., ["company P&L template"])
agent_nameNoName of the agent (e.g., "Marcus"). Used to look up agent_id if not provided.
skill_nameYesShort name for the skill (e.g., "13-Week Cash Forecast")
tools_usedNoTool names referenced in the process (e.g., ["get_cash_position", "create_google_sheet"])
activity_nameNoActivity this skill backs (e.g., "Weekly Cash Review"). If provided, the skill will be linked to this activity via skill_id.

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals that the tool is sensitive-tier and may require manager approval, with details about different approval modes. It also states it can both create and update skills. This adds meaningful transparency, though it could further clarify whether updates overwrite or merge.

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 concise, consisting of two short paragraphs. The first paragraph immediately states the purpose and usage context, while the second paragraph provides essential behavioral notes. Every sentence adds value with no wasted words.

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?

Given the complexity of 8 parameters (3 required) and no output schema, the description provides good context including usage examples and approval requirements. However, it does not explain what the tool returns (e.g., success message or skill object) or clarify the exact behavior of updates (e.g., whether it replaces or appends steps).

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 coverage is 100%, so the input schema already documents all 8 parameters with descriptions. The tool description does not add any parameter-specific meaning beyond what is in the schema. Therefore, the baseline score of 3 is appropriate.

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 clearly states it creates or updates a skill for an agent, with specific verb ('Create or update') and resource ('skill'). It distinguishes from siblings by emphasizing that skills teach agents HOW to perform activities, and provides concrete usage examples like '@Marcus here's how I want you to do the cash forecast'.

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 provides explicit trigger phrases for when to use the tool (e.g., 'Use when a user says...'), offering clear context for invoking it. However, it does not explicitly describe when not to use it or compare it to similar sibling tools like 'add_agent_activity', which would strengthen the guidance.

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

All freedom-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

The tool set is heavily disambiguated by detailed routing descriptions, domain prefixes, and lifecycle verbs, so most tools have a clear intended purpose. However, at 297 tools there are still close pairs and overlapping decision surfaces (e.g., approval workflows, 'what should I work on' readers, multiple finance/ads readers) that require careful description reading to avoid misselection.

Naming Consistency4/5

Naming is predominantly consistent snake_case verb_noun with strong domain prefixes like shopify_, x_, posthog_, and list_/create_/update_ patterns. Minor inconsistencies exist, such as several collection-returning tools using get_ (get_team_members, get_icps, get_okrs) instead of list_, and some generate_ vs create_ vs draft_ verbs, but the pattern is still predictable overall.

Tool Count1/5

297 tools is an extreme outlier and far beyond a usable MCP tool surface. Even a large suite has no justification for this count in one server; the agent would struggle to select among hundreds of similarly descriptive tools, and the natural 3-15 tool range is exceeded by nearly 20x.

Completeness4/5

The individual domains represented — OKRs, CRM/leads, Shopify, content pipelines, ads, PostHog, team hiring, knowledge, finance, and session management — are covered remarkably well with full lifecycle patterns. Minor gaps exist, such as no full deal CRUD, no delete for several Google/Shopify artifacts, and some analytical surfaces being read-heavy, but most workflows can be completed without dead ends.

Resources