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

Goes well beyond the readOnly/idempotent/openWorld annotations with a concrete cost model (1 credit per URL, +4 for summary, +4 for output_schema), a refund policy for failed URLs and failed AI steps, and a timeout consequence ('slower ones are reported as failed'). This is exactly the operational context annotations cannot express.

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?

Three sentences, no filler, with the core capability front-loaded and pricing last. Every clause carries information an agent needs for budgeting or parameter selection.

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?

Covers capability, modes, limits, and cost for a 9-parameter tool with a nested JSON Schema parameter and no output schema. Minor gaps (per-page failure reporting shape, interaction of max_tokens with highlights) are handled acceptably by the schema descriptions.

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 89%, so the baseline is 3; the description earns an extra point by explaining the coupling between query and highlights (ranked passages vs full page) and the role of output_schema, which is the non-obvious interaction an agent must get right. Prompt, country, timeout, and max_tokens are left to the schema and are adequately documented there.

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 (read) and resource (URLs, HTML or PDF) plus the output format (clean Markdown) and a hard limit of 20. This is immediately distinguishable from retrieval siblings like search, crawl, or webpage, which fetch or index rather than convert URLs to Markdown.

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?

Explicitly maps three mode combinations to outcomes: query + highlights yields ranked passages, summary yields a short summary, output_schema yields structured JSON. It does not state when to prefer this over the webpage or crawl siblings, so routing guidance is good but not exhaustive.

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