Проводит доказательный аудит сайтов по действующему законодательству РФ: сканирует публичные страницы, формы, cookies, документы, платежные сценарии и внешние сервисы, сверяет применимые требования и возвращает отчет с рисками, источниками и готовым планом исправлений для Codex. Expected Runtime: ~180s.
| Name | Required | Description | Default |
|---|---|---|---|
| payload | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the full behavioral burden, and it does so well by enumerating what is scanned and what the final report contains. It also discloses the expected runtime of ~180s. It stops short of stating whether the scan is strictly read-only, what authentication is required, or what happens if the site is unavailable, but overall behavior is clearly conveyed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded: the core action appears first, supported by a concise checklist of scanned elements and the final deliverable. The runtime note is a single useful addition with no filler, making every sentence purposeful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a specialized audit agent with an output schema, the description gives sufficient high-level context: what it scans, what it returns, and how long it takes. The main gap is the under-specified URL parameter and lack of any prerequisite or limitation note, which prevents it from being fully complete for invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides only a single 'url' property with an empty description, and the tool description does not compensate for the 0% schema description coverage. The description mentions auditing sites, which implicitly points to the URL parameter, but it does not clarify expected URL format, whether the URL must be a domain root or any public page, or how it should be passed inside the payload.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: it conducts an evidence-based audit of websites against current Russian legislation. It further clarifies scope by naming scanned artifacts (public pages, forms, cookies, documents, payment scenarios, external services) and the deliverable (report with risks, sources, remediation plan), making it distinguishable from generic research or browsing siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The intended use case is implied strongly: use this tool when a Russian-legal compliance audit of a website is needed. However, the description does not explicitly say when not to use it, does not mention prerequisites such as site accessibility or ownership, and names no alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools overlap in purpose, particularly the research/analysis agents (constructivecritic, firstprinciplesanalyst, scientificresearchagent, researchagent) and the three reasoningdelegation agents, which differ only by effort level. Some tools like 'exploitagent' and 'testagent' have vague descriptions that don't clarify distinct roles. However, many tools are clearly distinct (e.g., campbuddy vs. smart_fridge___nutrition), and the core router tools (discover_agents, a2a_call_agent, wait_for_task) are well-defined.
Naming is inconsistent: some tools use snake_case (a2a_call_agent, discover_agents, wait_for_task) while most others are camelCase or concatenated lowercase (browsernavigationagent, campbuddy, reasoningdelegationhigh). There's also odd naming like 'smart_fridge___nutrition' with triple underscore, and simple names like 'testagent' and 'exploitagent'. No consistent convention exists across the set.
With 24 tools, this is near the upper limit but still reasonable for an agent router that hosts many pre-defined specialized agents. The core router functions (discover, call, wait) are supplemented by a diverse set of agent tools. It's borderline heavy but each tool represents a distinct agent or action, so it's acceptable.
The router functionality is well-covered: discovery (discover_agents), synchronous calling (a2a_call_agent), asynchronous handling (wait_for_task), and skill lookup (search_skills/get_skill) for extension. Missing are explicit cancellation or task management tools, but core workflows are supported. The presence of domain-specific agents (campbuddy, silpo_home_restaurant) doesn't detract from router completeness.
