FREE request validation before buying AgentLLM Micro. Pass the exact prompt, optional system instruction and max_tokens. It checks the 2,400 UTF-8-byte, 8-message and 300-output-token limits without calling a model or charging anything. Continue to agentllm_micro only when ready_to_buy is true.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| system | No | ||
| max_tokens | No |
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, the description carries the full weight of behavioral disclosure. It explicitly states that the tool does not call a model or charge anything, and it names the exact checks (2,400 UTF-8-byte limit, 8-message limit, 300-output-token limit). It doesn't describe error behavior or return structure, but the 'ready_to_buy' gate is a meaningful behavioral clue.
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 three sentences with no filler; it defines the purpose, the parameter expectations, and the decision rule to continue to the sibling. Every sentence contributes necessary information and the core behavior is front-loaded.
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?
Given no output schema and no annotations, the description provides the essential operational details: what to supply, what is checked, and what to do after (proceed only when ready_to_buy is true). It is slightly ambiguous about where ready_to_buy comes from but sufficient for an agent to invoke and interpret partially.
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?
Schema description coverage is 0%, so the description must compensate. It covers all three parameters: 'the exact prompt' (prompt), 'optional system instruction' (system), and 'max_tokens.' The mention of the 300-output-token limit adds context to max_tokens beyond the raw schema.
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, actionable purpose: 'FREE request validation before buying AgentLLM Micro.' It explains it validates prompts against explicit limits and clearly distinguishes itself from the paid sibling agentllm_micro by framing this as a pre-purchase gate.
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?
It indicates exactly when to use this tool ('before buying') and instructs to proceed to agentllm_micro only when ready_to_buy is true, effectively naming the sibling and the activation condition. It doesn't list alternative scenarios or explicitly state when not to use it, but the usage context is strong.
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.
Many tools are clearly separate (validate_vat, validate_iban, token_status, tx_status), but several overlap by combining the same core checks: check_counterparty_eu, must_verify_before_pay, tx_preflight, and invoice_to_pay_dossier_eu all screen sanctions and/or do VIES/IBAN checks. The descriptions help, but the boundaries between a KYB check, a payment gate, and a transaction preflight are subtle enough that agents can easily pick the wrong one.
Names are uniformly lowercase snake_case, and patterns like validate_*, prepare_*, and *_eu give some predictability. However, the verb style is inconsistent: some tools are verb-led (read_url, screen_sanctions_eu, lookup_company_eu), others are noun-led (market_data, token_status, agentllm_micro), and paid/prepare pairs do not share a consistent naming scheme.
24 tools is at the upper edge of what is reasonable, and the server mixes several unrelated concerns: EU VAT/invoice compliance, sanctions/KYB, US import readiness, AI disclosure/LLM inference, market data, URL reading, and transaction status. The core comply-to-pay workflow is well represented, but the extra domains make the tool list feel heavier and less like a single coherent service.
The EU invoice/payment compliance flow is fairly complete: e-invoice validation, VAT rules, VIES, IBAN, sanctions, transaction preflight, payment decisions, bookkeeping statements, and receipt verification are all covered. Obvious gaps remain for such a broadly named server: no export/other product compliance, no broader EU regulatory coverage, and the key invoice guard explicitly does not cover duplicate-ledger detection, internal approval, or delivery checks.
