report

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

With no annotations, the description carries the full burden. It discloses that the tool expects pre-collected findings and that save_html optionally writes a file. This is useful, but it does not explicitly state whether the tool is read-only, what happens if save_html is empty (e.g., returns HTML string), or any side effects beyond file writing. The description is moderately transparent but lacks depth.

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 concise and well-structured. A single opening sentence states the purpose and input sources, followed by a clear Args block that maps each parameter to its meaning. Every sentence earns its place, and the information is easy to scan.

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?

The description covers all input parameters and gives a clear picture of the tool's behavior. An output schema exists, so return values are handled. The main gap is that it does not address the relationship with sibling tools report_web and report_source, which could confuse an agent about which tool to choose. Otherwise, the description is complete for a report-generation tool.

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?

The description provides detailed semantics for each parameter, far exceeding the schema. It explains findings_json as a JSON array with a specific shape (title, severity, vuln_class, etc.), target as the assessed target's name/URL, kind as 'web' or 'source', and save_html as an optional path. This is essential because schema description coverage is 0%, and the description fully compensates.

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's purpose: 'Render a report from findings you have ALREADY collected.' It names specific verbs ('Render') and resources ('report') and provides context about the input (findings_json). However, it does not explicitly differentiate this tool from the sibling tools report_web and report_source, which likely serve specialized versions of the same purpose.

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 implies usage context: it should be used after findings have been collected, e.g., from 'hunt/review' or 'http_send/intruder.' This gives a clear when-to-use signal. However, it does not mention any exclusions or alternatives, such as when to use report_web or report_source instead. The guidance is implied rather than explicit, so it falls short of a 4.

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