Autonomous TLPT simulation: generates TIBER-EU scenarios, maps MITRE ATT&CK, creates findings, rates detection. Art. 26.
| Name | Required | Description | Default |
|---|---|---|---|
| entity_id | Yes | ||
| scenarios | No | Number of scenarios (default: 3) |
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 burden of behavioral disclosure. It lists the operations (generate, map, create, rate) but does not disclose any side effects, prerequisites, permission needs, or expected outcomes. The phrase 'creates findings' hints at persistence, but whether it mutates databases or requires specific setup is unknown.
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 a single sentence that front-loads the core purpose ('Autonomous TLPT simulation') and lists the key actions without filler. Every part contributes to understanding, and 'Art. 26' adds a regulatory reference without bloating the text.
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?
This is a complex tool with no output schema and no annotations, but the description does not explain return values, expected outputs, or how the pieces relate. It also omits context about prerequisites or whether this is a long-running operation, making it incomplete for an agent that needs to know what to expect after 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?
Schema coverage is only 50% (the 'scenarios' parameter has a description, but 'entity_id' does not). The tool description adds no parameter-level information, leaving entity_id completely unexplained. With no description of what entity_id refers to or how scenarios count affects the simulation, parameter semantics are weak.
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 clearly states a specific verb and resource: it performs an autonomous TLPT simulation that generates TIBER-EU scenarios, maps MITRE ATT&CK, creates findings, and rates detection. This distinguishes it from siblings like generate_scenarios or mitre_map by emphasizing a full end-to-end automated process.
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 word 'Autonomous' implies usage for a full simulation run, but there is no explicit guidance on when to use this tool versus alternatives like generate_scenarios or finding_register. No exclusions or alternative comparisons are provided, so usage context remains implied rather than explicit.
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.
Most tools have distinct purposes, but potential confusion exists between 'auto_simulate' and 'generate_scenarios' (both involve scenario generation) and between 'health_check' and 'ping' (both test connectivity). Descriptions help mitigate but do not eliminate ambiguity.
Tool names consistently use snake_case but mix verb-based (generate_scenarios, register_exercise) and noun-based (evidence_bundle, threat_profile) patterns. 'ping' is a single word, breaking the pattern. This inconsistency may confuse agents about whether a tool performs an action or represents a resource.
17 tools cover the breadth of TLPT activities (scoping, simulation, findings, compliance) without being overwhelming. Each tool serves a distinct part of the workflow, making the count well-scoped for domain complexity.
The tool set covers major TLPT lifecycle phases: preparation (threat_profile), scenario generation (generate_scenarios, auto_simulate), execution mapping (attack_chain, mitre_map), findings (finding_register, remediation_plan), compliance (obligation_map, sync_to_ampel), and scheduling (test_calendar). Minor gaps like a dedicated reporting tool exist but can be worked around.