fsv_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 so well: it discloses that aggressive mode raises rate/concurrency, that the scan is time-boxed by max_minutes with partial results kept, that the crawl skips logout/asset links, that ct_logs sends the domain to a third party (crt.sh) and requires consent, and that authenticated scanning should use a test account. These are the exact behavioral facts an agent needs and that structured fields do not provide.

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 front-loaded with the core action and the profile enum, and nearly every clause adds a fact an agent needs (consent for crt.sh, time-boxing, authorization). It is a dense single block, though, and the parameter notes would read better as a short list than as an inline stream of clauses.

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?

This is a complex 14-parameter, potentially intrusive scanning tool with no annotations; the description covers authorization, third-party data exposure, time-boxing, and mutating scan behavior, and an output schema exists so return values need not be detailed. The main gap is that module selection and the crawl/depth/max_urls limits are left entirely to the schema titles.

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%, so the description must compensate and it largely does: it explains profile values and default, max_minutes default and partial-results behavior, use_ct_logs' third-party implication, allow_external's effect, seed_urls' role, and the headers/cookies authentication intent. It leaves crawl, depth, max_urls, modules and exclude_paths undocumented (notably module names are never explained or pointed to fsv_list_modules).

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 opens with a specific verb and resource: 'Run a web vulnerability scan against a target URL', then specifies what the scan does (crawl same-origin, run modules by profile). This is clearly a full scan rather than a quick check or WAF check, but the description never explicitly names the sibling tools (fsv_quick_check, fsv_waf_check) to route the agent. Solid but no explicit sibling differentiation.

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?

It gives clear when-to-use guidance for each profile ('passive' sends no payloads vs 'balanced' adds active checks vs 'aggressive' higher concurrency), for use_ct_logs (only with user consent), for allow_external, and for headers/cookies (authenticated scan with a test account). It also states the authorization precondition and that authorized=true should only be passed after confirmation. It does not explicitly say when to prefer a sibling tool like fsv_quick_check instead, so not a 5.

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