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

With no annotations provided, the description fully carries the transparency burden. It discloses active adversarial probing, per-scan credit consumption, output format (Markdown report), and the specific audit behavior for MCP targets (tool-poisoning and over-broad capabilities). While it could also mention potential side effects on the target (e.g., resource exhaustion from deep probes), the 'active and adversarial' warning is sufficient for an agent to understand the tool's impact.

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 efficient and front-loaded, beginning with the primary purpose and then providing essential context (target kinds, prerequisites, authorization). It is slightly long (4 sentences) but every sentence carries unique information: purpose, scope, supported kinds, cost, and safety. No redundancy with the schema is evident.

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 the tool's complexity, lack of annotations, and absence of an output schema, the description is remarkably complete. It covers the purpose, supported target types (with behavior for each), API key and credit prerequisites, output format, and authorization constraints. It provides enough detail for an agent to correctly select and invoke the tool without needing further clarification.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema. It clarifies that kind='mcp' triggers a tool-manifest audit, and it explains the API key distinction (the user's ScanLabsAI key vs. the optional target apiKey). It also contextualizes the 'deep' parameter with 'jailbreak + resource-exhaustion' via the schema, which the description reinforces. This adds actionable nuance to the parameters.

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 action ('Red-team an AI agent for security weaknesses'), enumerates the exact vulnerabilities it targets (prompt injection, system-prompt leakage, sensitive-data disclosure, unsafe output handling, excessive agency), and explicitly distinguishes itself from siblings by noting it is 'agent-to-agent scanning' versus other scan tools. This fully differentiates it from scan_website and compliance_report.

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 description provides clear when-to-use context: 'use it to assess another agent from here.' It also specifies supported target kinds, prerequisites (ScanLabsAI API key, credits), and an explicit authorization boundary ('only scan agents you own or are authorised to test'). It does not explicitly name alternative tools for non-agent targets, but the agent-to-agent framing makes the usage context unambiguous.

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