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

With no annotations, the description carries the full burden and does: SSRF-safe, refuses pages that opt out via noai, truncation via max_chars, paid access ($0.002 USDC on Base or Solana via x402). These are exactly the constraints an agent needs before invoking.

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 the usage condition, then input, output, safety, payment. Dense but every clause carries information. The telegraphic 'English brief:' / 'Example:' fragments are slightly harder to parse than prose but not wasteful.

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 exists, yet the description enumerates the returned fields (markdown, title, language, finalUrl, chars, truncated) and covers payment, SSRF, and noai refusal. For a 3-parameter read tool this leaves nothing an agent needs 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%, so the baseline is 3, but the description adds real value: the 500-60000 range for max_chars (the schema only states the default) and the meaning of flags=1 as rule-based prompt-injection signalling. It does not explain the number|string union for max_chars.

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 concrete verb and resource (fetch a URL, return clean Markdown with boilerplate removed and tables kept) and the exact output shape. It also distinguishes itself from the brief and search+read variants by naming those endpoints, so an agent can pick it apart from web_read_brief and web_search_read without opening a 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?

'Use when an agent already has a URL' gives an explicit precondition that separates it from search-first siblings. It points at alternatives (/v1/web/read/brief, /v1/web/search-read) but by endpoint path rather than sibling tool name, leaving a small inference step.

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