Assess web apps in one call by checking headers, tech, crawl, sensitive paths, TLS, CORS, and secrets. Use deep mode to add reflection testing and hidden parameter discovery.
One-call web application assessment: headers, tech, crawl, sensitive paths, TLS, CORS, secrets.
deep=True adds reflection testing and hidden parameter discovery on the parameters found.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| deep | No |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries full disclosure duty. It does disclose a meaningful behavioral trait — that deep=True performs reflection testing and hidden parameter discovery, i.e. more invasive and noisier requests — but it omits runtime expectations, scope/permission prerequisites, whether findings are auto-recorded, and what the caller gets back.
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?
Two compact sentences with the aggregate scope front-loaded in a scannable enumeration, and the modifier flag explained second. No filler, no repetition of the tool name as a sentence.
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 an aggregate tool that fans out to many checks, with no output schema and no annotations, the description should say roughly what comes back (structured findings? added to engagement?) and whether it is slow or noisy. Those gaps matter more here than they would for a single-check sibling.
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% across two parameters. The description explains 'deep' well (adds reflection testing and hidden parameter discovery on the discovered parameters), but 'url' is only inferable from the tool name and context — nothing states whether it accepts a hostname or full URL, or how in-scope targets are validated.
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 names a specific composite action ('One-call web application assessment') and enumerates the covered checks: headers, tech, crawl, sensitive paths, TLS, CORS, secrets. That enumeration implicitly separates it from the granular siblings (pentest_web_headers, pentest_web_cors, pentest_web_secrets_scan), but it never names those siblings or states the aggregate-vs-single distinction explicitly.
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 'One-call' framing and the deep=True clause imply when to use it (broad first-pass assessment, escalate to deep when parameters need probing), but there is no explicit when-not guidance, no mention of preferring the individual tools for targeted checks, and no prerequisite such as confirming scope.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.