ComOS Federation

introspection_system_change_graph

Read-onlyIdempotent

Return the dependency graph of change orders across every registered ComOS repo: nodes (slug/repo/declared+filesystem parent/children/interests), parent/child edges (source: frontmatter | filesystem | both), interest edges (CO 2026-05-30-021 — a declared cross-repo stake, source: frontmatter | link), and first-class drift reports where frontmatter and directory disagree. Never silently reconciles drift. Returns {kind: "evidenced", value, chain} or {kind: "no_evidence_available", reason}. Added by comai-plan CO 013-003 / federation CO 006. Returns: The change graph: nodes (changes) and edges (their connections). Example: call introspection_system_change_graph with arguments {}.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedAug 9, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true, destructiveHint=false, and the description adds that drift is reported but never silently reconciled—clarifying a key behavioral boundary. This goes beyond annotation, though it doesn't discuss auth or rate limits.

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?

Description is detailed but not bloated; it front-loads the core purpose and packs node/edge/drift reporting into a single sentence. The example call is a minor extra, but overall efficient.

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?

No output schema exists, yet the description fully specifies the two possible return shapes (change graph vs. no-evidence) and the structural elements (nodes, edges, drift). Covers behavior, scope, and examples relevant for a zero-parameter read-only tool.

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?

Tool has zero parameters command schema is empty, so the baseline is 4. The description adds nothing about parameters (none exist), but it does explain the return shape, which is useful.

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?

Description clearly states the tool returns the dependency graph of change orders across all registered ComOS repos, specifying node/edge types. This is distinct from sibling tools like introspection_system_diff or introspection_system_list_nodes, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. It provides an example call but lacks any 'use when' or 'prefer this over X' context, leaving selection to the agent's inference.

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

All ComOS Federation 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

Tools are grouped by clear domain prefixes (federation_*, introspection_*, moltbook_*) with each targeting a distinct resource+action (bond_post/release/status, key_challenge/bind/status, journal_append/read). The primary near-overlap — catalog_search_multi vs catalog_search_grouped_multi — is explicitly disambiguated in descriptions. Minor confusion risk exists among the four knowledge tools (federation_help, federation_why, about_us_about, how_to_about) but their purposes (how/why/manual/walkthrough) are distinct enough.

Naming Consistency3/5

The dominant `federation_<verb>_<noun>` pattern (create_tenant, list_agents, bond_release) is strong, but it's mixed with bare-noun tools (federation_arena, federation_offer, federation_solvency, federation_pricesheet, federation_help) and noun-noun variants (federation_manager_tree, federation_tenant_info). Non-federation tools use a loose `<domain>_<verb>` or single-token convention (legal_get, web_research, about_us_about). Readable overall, but conventions are noticeably mixed across the surface.

Tool Count2/5

At 72 tools this crosses the 50+ threshold for an extreme count. While the federation's scope is genuinely broad (manager lifecycle, tenants, catalog, agents, bonds, keys, journal, canon, introspection, social, email, research), the surface is bloated — roughly 15 bare introspection tools (list_nodes, probe, confidence, diff, coverage_gaps, co_decisions, climb_history, change_graph, change_reach, corpus_*) cover meta-self-knowledge that could plausibly collapse into fewer verbs. Agents would face a very large selection space.

Completeness5/5

The tool surface is exhaustively complete for the federation domain: applicant and operator sides of admittance, full manager lifecycle (create/list/freeze/attest/bond/key), full tenant lifecycle (create/list/info/update/suspend/delete/enter), catalog discovery with change-detection, pricing, solvency, latency, journaling, governance, legal, and even external outreach (email/moltbook/research). No dead ends exist — every write has a corresponding read/status path, and branched platform tools are intentionally deferred behind enter_tenant rather than omitted.

Resources

Need Help?