Skip to main content
Glama

Red by Big Red Cloud

by io.github.BigRedCloud

Clear Audit Log

brc_clear_audit_log
Destructive

Clear the Red audit log for this MCP server session. A call without confirmWrite: true returns confirmation_required and a payload preview. confirmWrite: true applies the previewed change after explicit confirmation. Passing preflight is not confirmation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
confirmClearNoMust be true to confirm that the session audit log should be cleared.
confirmWriteNoMust be true only after a plain-English preview before posting has been shown in the current conversation and the user explicitly confirmed posting (for example yes, create it / post it now / confirm). Never set true on the first call or because the user initially asked to create something. Nothing is written to Big Red Cloud until you confirm.
connectionRefNoOpaque Red connection reference returned by brc_confirm_company_connection. Pass this exact value on every later tool call when the MCP client rotates session ids (for example Vibe/Mistral). Keep reusing the same connectionRef after successful tool calls — do not start a new connection because a lookup returned empty or partial data. It is not an API key and does not contain credentials.

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already carry destructiveHint=true and readOnlyHint=false, and the description adds materially richer safety context: unconfirmed calls return confirmation_required with a payload preview, confirmWrite: true only applies after explicit user confirmation, and preflight is not confirmation. It also narrows the blast radius by scoping the action to the MCP server session.

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?

Three sentences, no wasted words: the core action and scope are front-loaded, then the unconfirmed path, the confirmed path, and the preflight caveat each get one earned sentence. Nothing duplicates the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive gated tool with no output schema, it discloses the unconfirmed response (confirmation_required plus payload preview) but not the confirmed/success response. More importantly, it never mentions confirmClear — the parameter literally named for this action — so an agent cannot be certain of the full confirmation protocol.

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 description coverage is 100%, so the baseline is 3 and the description need not restate parameter docs. It adds flow-level meaning around confirmWrite, but it never clarifies the relationship between confirmClear and confirmWrite, leaving an agent unsure whether one or both booleans must be true.

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 names a specific verb, resource, and scope: 'Clear the Red audit log for this MCP server session.' It distinguishes cleanly from the viewing sibling brc_list_audit_log and from the brc_clear_company_api_key / brc_clear_all_company_api_keys tools, which target a different resource.

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

Usage Guidelines3/5

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

The description explains how the confirmation flow works but never states when to choose this tool versus alternatives; brc_list_audit_log is not named as the viewing counterpart, nor are the other clear-* siblings excluded. Usage is implied by the name and scope rather than explicitly routed.

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

All Red by Big Red Cloud 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

B3.2/5.0
Disambiguation4/5

Most tools have a clear single resource-and-action focus, and the systematic naming helps an agent separate create/get/update/delete/list operations. The main confusion risks are the help/search cluster (red_help, find_help_resources, get_help_resource_details) and the payment/cash-payment/batch-payment variants, which require careful reading of the descriptions to avoid misselection.

Naming Consistency4/5

The brc_ prefix with snake_case verb_noun naming is used consistently across the vast majority of tools, e.g. brc_list_customers, brc_create_sales_invoice, brc_delete_purchase. A few noun-style names like brc_company_readiness_check, brc_grouped_nominal_accounts_report, and brc_red_help break the pattern, but these are minor deviations.

Tool Count1/5

159 tools is an extreme count for an MCP server, well beyond the 50+ threshold described as an extreme mismatch. While the accounting domain is broad, the surface is inflated by batch variants, generated-reference variants, and without-dormant list variants that could be consolidated.

Completeness4/5

Core accounting entities have strong lifecycle coverage: customers, suppliers, products, sales reps, bank accounts, quotes, sales invoices/entries/credit notes, purchases, payments, cash receipts, accruals, prepayments, and nominal journal batches all support relevant CRUD and batch operations. Minor gaps include the quote update being limited to the reference only, no update/create tools for VAT categories or company settings, and email sending being limited to quotes, invoices, and statements.

Resources