Meta Council

Audit Export

audit_export

Read-onlyIdempotent

Export this workspace's own agent-action audit trail as structured events, oldest first, for loading into a SIEM. Each event carries what triggered the action, which identity authorized it, which resource was touched, the outcome, and the error state. Metadata only -- no prompt text, document content, tool arguments, or model output is ever returned. Filter by date range and event action; page forward with the cursor each response returns. Covers a documented subset of platform activity rather than every action: see docs/WORKSPACE_AUDIT_EXPORT.md, and note that the coverage block on every response lists exactly which actions are exportable and which are not. Requires authentication and the audit:read scope.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Events per page. Defaults to 100, maximum 500.
`since`	No	ISO-8601 lower bound, inclusive, for example 2026-08-01T00:00:00Z. Omit for no lower bound.
`until`	No	ISO-8601 upper bound, inclusive. Omit for no upper bound.
`action`	No	Exact event action to filter to, for example mcp.tool_call. Omit to return every action this workspace can export.
`after_id`	No	Resume cursor. Pass the next_cursor from the previous page to continue without re-reading it.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description adds: metadata only (no content returned), coverage block on responses lists which actions are exportable, requires auth and audit:read scope. It doesn't delve into error cases or rate limits, but the annotations cover safety profile; a 4 is appropriate for the extra security and data-scope context.

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 dense block that front-loads the purpose and data scope, then adds filter/pagination info, then coverage caveat and auth. Every sentence earns its place; no filler.

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?

Given the tool's moderate complexity (5 params, pagination, auth, coverage limits) and generous schema coverage plus output schema present, the description fully covers purpose, scope, exclusions, and prerequisites. It is complete enough for an agent to select and invoke it correctly.

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 schema already documents all 5 params including examples. The description adds meaning by connecting the pattern: 'page forward with the cursor each response returns' and maps after_id to next_cursor from the previous page. It doesn't add new syntax details beyond schema but reinforces the pagination model.

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 states precisely what the tool does: exports this workspace's own agent-action audit trail as structured events, oldest first. It also names the sibling tool 'get_workspace_metrics' as the alternative for platform metrics, and differentiates from 'get_meta_council_platform_metrics' and other metric lists by focusing on the audit trail.

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

Usage Guidelines5/5

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

The description explicitly says when to use it: for SIEM loading, and notes that it covers a 'documented subset of platform activity rather than every action', pointing to docs/WORKSPACE_AUDIT_EXPORT.md. It also clarifies the alternative: 'To get overall platform usage metrics, use get_workspace_metrics instead.'

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

All Meta Council 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

Disambiguation5/5

Every tool targets a distinct resource and action, with detailed descriptions that clearly separate overlapping domains (e.g., consulting vs. marketing vs. outreach). Even within the same domain, tools like 'create_consulting_deliverable' and 'create_consulting_document_revision' are unambiguous due to their specific nouns.

Naming Consistency5/5

All tools follow a consistent verb_noun snake_case pattern (e.g., 'create_invoice', 'get_deal', 'list_agents'). The few exceptions like 'locus_determine_from_scores' still adhere to the verb_noun structure and do not break the pattern.

Tool Count1/5

With 124 tools, the server is massively over-scoped for typical MCP use. The tool count far exceeds the '50+ extreme mismatch' threshold, making it nearly impossible for an agent to efficiently navigate or select the right tool without extensive context. Even a large platform should consolidate or expose fewer tools.

Completeness5/5

The tool surface covers CRUD and lifecycle operations across at least 10 domains (sales, consulting, marketing, outreach, accounting, workflows, ticketing, API keys, feedback, platform metrics). Each domain appears to have no obvious gaps—e.g., invoicing includes create, update, send, mark paid, void; ticketing includes create, update, archive, dependencies, batch, scenarios, validation.

Resources

Need Help?