agentscan: which AI crawlers, assistants, MCP clients and x402 buyers hit your site, from your access logs

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world with nothing fetched), and the description reinforces that while adding substantial context beyond it: hard line/byte limits refused before payment, in-memory-only processing, no IP returned, a latency budget, and an explicit warning that classes are UA-derived and spoofable plus a prompt-injection caution on returned text.

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?

Purpose is front-loaded and the pricing, size, latency and safety facts all earn their place for an agent budgeting a paid call. It loses a point for redundancy: 'In memory only, never stored and nothing fetched' is repeated by both 'The submitted text is never logged or stored' and the schema's own 'never stored' text.

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 a paid, single-parameter analysis tool with an output schema and full safety annotations, the description supplies everything an agent needs before invoking it: cost model and block limits, throughput, data-handling guarantees, and a trust caveat on returned data. Nothing material is missing.

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% and the single 'logs' parameter already documents accepted formats, the 1–100,000 line and 20 MB bounds, and the no-storage/no-IP guarantees. The description largely restates these rather than adding syntax or format detail the schema lacks, so the baseline 3 applies.

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 (analyze) and resource (AI crawler, assistant, MCP and x402 buyer traffic in access logs), and explicitly carves out scope by naming the sibling tools identify_x402_client and parse_user_agent for the single-User-Agent case. An agent can distinguish this from its 18 siblings without opening any schema.

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 provides explicit routing to alternatives ('For one User-Agent use identify_x402_client or parse_user_agent'), which is exactly the disambiguation an agent needs. It does not, however, state when-not to use it versus the bulk/index siblings or note prerequisites such as supplying correctly formatted logs.

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