zerodom_scan

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

With no annotations, the description carries the full burden and does well: it discloses scope (ACTIVE page only, not a crawl), output format (JSONL), and a genuine capability limit (a page cannot read its own Set-Cookie header). It does not state side effects or whether the scan is purely read-only, which keeps it from a 5.

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?

Front-loaded with the action and result format, then the operational caveats; no filler. The heavy parenthetical clauses make it denser than necessary but each still carries information the agent needs.

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?

Output schema exists, so return values need not be restated, and the description still names JSONL and the finding categories. Combined with the navigation prerequisite and the CLI-only exclusion, an agent has what it needs to call this correctly.

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 0%, so the description must explain the single `js` parameter, and it does: js=True means the callable API surface is read from the page's same-origin JS. It never states what js=False yields, but the default behavior is clear enough to invoke correctly.

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?

States a specific verb and resource (run zerodom's surface rules over the ACTIVE page) and enumerates the exact finding classes: interaction-graph rules, DOM-XSS sinks, callable API surface, and CSP/CORS header posture. This is clearly differentiated from siblings such as zerodom_probe or zerodom_read_page.

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?

Explicitly tells the agent when to use it ('Recon over the page you are on'), names the prerequisite sibling ('navigate first with zerodom_parse_url'), and carves out what it cannot do ('Cookie-flag and CSRF correlation are CLI `zerodom scan` only'), routing the agent away from a false expectation.

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