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

With no annotations, the description carries the full burden. It discloses key behaviors: single-target, not a crawler, rejects loopback/private/internal hosts, and returns a 'caution to review, never a verdict'. It also covers cost, latency, and what the scan does not do (does not follow links). Minor gap: it doesn't explicitly state whether it invokes the scanned tools, but 'read its advertised tools' implies static analysis.

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 well-structured with clear sections (overview, limitations, when to use/not use, inputs, returns, cost, latency). It's somewhat long but every section earns its place, and the main purpose is front-loaded. No redundant wording beyond necessary clarification.

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?

Despite having no output schema, the description fully documents return fields with types (`server`, `tools_scanned`, `flagged_count`, `risk`, `score`, `tools`). It also covers cost, latency, and safety limitations, making it significantly more complete than typical for a single-parameter tool. The only minor omission is an example, but that's not essential.

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% for the single `url` parameter, and the description's input section mostly restates the schema ('MCP server endpoint (http/https)'). It adds the note that `url` is in the body, but this is a minor addition. Baseline 3 is appropriate given high schema coverage; the description adds minimal new semantics.

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 the tool scans a caller-supplied MCP server for injection vulnerabilities and dangerous capabilities, using specific verbs ('Connect', 'read', 'run', 'flags') and resources ('MCP server', 'tool name / description / input schema'). It explicitly distinguishes from siblings by noting it is NOT a crawler and provides alternative tools for other use cases.

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 explicit 'Use this tool when' and 'Do NOT use this tool when' sections, with named alternatives (`scan_injection` for text blobs, `cross_lens_verify` for trust verdicts). It also clarifies limitations like single-target and caller-initiated, making the appropriate context unmistakable.

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