search_scans

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

With no annotations, the description carries the burden of disclosing behavioral traits. It adds useful context by stating 'Works without an API key, at lower rate limits,' which informs about authentication and rate constraints. However, it does not elaborate on other behaviors such as pagination, sorting, or any limits on the 'size' parameter. The rate-limit mention adds significant value, but not enough for a higher score.

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 one-sentence definition, followed by a curated list of useful fields, then three concrete examples. Every part contributes to understanding how to invoke the tool. It is appropriately sized for the complexity and avoids redundant or extraneous information.

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 tool has an output schema, so return values are already specified. The description covers the main functionality, query syntax, useful fields, and even rate-limit behavior. It is complete enough for an AI agent to construct valid queries, though it could have briefly mentioned that it's the general-purpose alternative to the specialized search tools. The examples and field list make it largely sufficient.

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 schema has 0% description coverage, so the description compensates by providing a detailed field list and query examples that clarify the syntax and semantics of the 'query' parameter. While the 'size' parameter is not described, it has a default and is self-explanatory. The query examples offer meaning well beyond the bare schema type, leading to a score of 4.

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 function: 'Search historical urlscan.io scans with an ElasticSearch query string.' This specifies the verb, resource, and method, and distinguishes it from sibling tools like 'search_by_domain' or 'search_by_ip' by emphasizing the flexible ElasticSearch query capability. The inclusion of useful fields and examples reinforces the 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 gives clear context on how to use the tool through examples and a list of searchable fields, making it apparent that this is for ad-hoc, query-based searching rather than specific lookups like by domain or IP. It does not explicitly state when not to use it or name alternatives, but the sibling names and the tool's generic nature imply appropriate usage. There is no exclusion guidance, so a 4 is appropriate.

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