page_extract

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 null-for-unstated-fields semantics, the 25-field cap, the underlying model, prompt-injection handling ('page content is treated as data, instructions inside it are ignored'), the no-charge condition, cost, and p99 latency. These are exactly the behavioral traits an agent needs and cannot get from structured fields.

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?

Front-loaded with purpose, mechanism, and output contract before the operational details (model, cost, latency). It is dense but every clause carries information; it reads as one long paragraph rather than cleanly separated sections, which keeps it short of a 5.

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?

No output schema or annotations exist, yet the description specifies the return contract (exactly the requested fields, typed and validated against a JSON schema, null when unstated) plus billing and latency behavior. Nothing material is missing for correct invocation.

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%, so baseline is 3, but the description adds real meaning: a concrete field-definition example, the supported type list, and the 'up to 25 fields' limit that the schema does not state. It exceeds the schema without fully replacing it for every parameter.

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+resource ('Extract structured JSON from a web page or text') and immediately names the distinguishing mechanism: caller-defined fields. An agent can separate this from siblings like page_summarize, webpage_reader, and pdf_extract 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?

Gives concrete use cases ('product data, prices, contact and company details, job postings, event data, specs') and the input modes (url or text), which is clear context for when to reach for it. It stops short of naming alternatives or stating when NOT to use it (e.g., use pdf_extract for PDFs), so it does not reach a 5.

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