freedom-mcp

request_attention_spawn

Request a NEW local coding session from voice/chat (tab spawn). Queues a sticky for the desk launcher on THIS operator's machine (host must run attention-launcher). Use when they say "start a Grok/Claude on …", "new build for …", "open a session for …". Does not open a cloud IDE — the local launcher opens Terminal + announces + optional first directive.

[write-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

Name	Required	Description
`cwd`	No	Working directory on the operator machine (e.g. /Users/…/GitHub/freedom-ai). Prefer absolute paths they already use.
`goal`	Yes	One-line goal for the new session (1–500 chars).
`host`	Yes	Which builder to open: grok (Terminal) \| claude-desktop (Claude.app Code — preferred) \| claude-code (Terminal CLI)
`companyId`	No	FreedomOS company id to act within (you must be a member). Required for company-scoped tools.
`session_id`	No	Optional stable session id; default auto-derived from host + project.
`first_instruction`	No	Optional first work sticky delivered after the new session announces (imperative).

TDQS

A4.2/5.0

Behavior4/5

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

Since no annotations are provided, the description carries full responsibility. It discloses the local spawning mechanism, prerequisite (host must run attention-launcher), and the write-tier approval behavior (first use may require approval, from-now-on vs just-once). It also explicitly states what it does not do (cloud IDE). This provides sufficient transparency for the agent.

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 a single paragraph plus a bracketed note. It is front-loaded with the core purpose, followed by mechanism, usage examples, limitations, and approval details. Every sentence adds value with no fluff, making it highly concise and well-structured.

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?

The description covers the tool's functionality, prerequisites, usage cues, and behavioral nuances (approval tiers). However, it omits any mention of the return value or expected outcome, which would be helpful given no output schema. Overall, it is fairly complete for an agent to decide when and how to use the tool.

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?

The input schema already has 100% coverage on all 6 parameters with descriptions. The description only indirectly references the first_instruction parameter as 'optional first directive' and implicitly indicates required fields. It does not add significant new semantic nuance beyond the schema, so 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 requests a NEW local coding session from voice/chat, queues a sticky for the desk launcher on the operator's machine. It distinguishes from cloud IDE and provides example trigger phrases, making the purpose very specific and distinguishable from sibling tools.

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 usage cues ('Use when they say...') and clarifies that this tool does not open a cloud IDE, indicating its local-only scope. It does not explicitly state alternatives or when not to use it, but the examples are clear enough for an agent to infer appropriate usage.

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

All freedom-mcp tools Inspect

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

Need Help?