scrape

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

With no annotations, the description carries the full behavioral burden and does meaningful work: it discloses caching semantics (max_age seconds, 0 = fresh), the three render modes including when a real browser is used, that actions can drive interaction before capture, geo/language targeting via location, and an explicit prompt-injection warning that returned content is untrusted data. It stops short of error/failure behavior, rate limits, or whether the call is billed, which for a network fetch tool an agent would benefit from knowing.

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?

It is front-loaded with the core capability and then organized as a compact param: meaning list, with essentially no filler sentences. The telegraphic style is efficient but dense — the actions grammar and formats enumeration run together, which slows parsing slightly.

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 12-parameter tool with no annotations and no output schema, the description covers the high-value parameters and the security caveat, which is enough to call it correctly in most cases. The remaining gaps — only_main, mobile, wait_for, and any notion of what the response looks like per format — are real but secondary.

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 enumerates the accepted formats values, explains query as a content filter, gives the render enum (auto/always/never), defines include_tags/exclude_tags as CSS selectors, sketches the actions object types, and explains max_age and location keys. Undocumented are mobile, only_main, wait_for as a top-level parameter, and the url format conventions, so the compensation is strong but incomplete.

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?

"Read one web page, PDF, Word, Excel or PowerPoint file" gives a specific verb, a concrete resource set, and a scope qualifier ("one") that implicitly separates it from crawl/batch_scrape. It never names a sibling explicitly, so an agent must infer the single-page vs multi-page boundary from that one word.

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?

Usage is only implied: "one" page signals this is the single-URL tool versus crawl, batch_scrape, or map_site, and the formats list hints at extraction use cases. There is no explicit "use this when... instead use X when..." statement, no prerequisites, and no note about when a crawl or search would be a better entry point.

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