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

Goes well beyond the readOnly/openWorld annotations: discloses the verification checks performed (block pages, CAPTCHAs, login walls, empty JS shells), automatic retry/headless-browser escalation, the billing rule (charged only on success), the default return format, and the failure-reason vocabulary (blocked:cloudflare, http_404, expect_text_missing). This is exactly the operational context an agent needs before spending credits.

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?

Four tight sentences, front-loaded with purpose, then verification behavior, billing, default output, and failure handling. Every sentence contributes a distinct operational fact with no repetition of the schema.

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?

There is no output schema, yet the description supplies the return shape (markdown by default, ok flag, reason string with example codes) and the cost model. Combined with a fully documented 5-parameter schema, an agent has everything needed to call this correctly and interpret the result.

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 100% and each parameter already documents its meaning, including the credit ladder for max_cost and the expect_text/expect_selector semantics. The description adds only marginal parameter meaning ('returns markdown by default') and introduces the ok/reason response fields, so the baseline of 3 is right.

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 and resource ('Fetch a public URL and get its content') plus the key qualifier that content is returned only if it genuinely loaded. It is clearly distinct from domain_reliability by implication (page content vs. domain reputation), but never names or contrasts with the sibling explicitly.

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 a concrete when-not rule: if ok is false, the reason explains why and the caller should not retry the same URL with the same settings. It also notes retries through other routes happen automatically, so the agent knows not to orchestrate fallbacks itself. It stops short of stating when to prefer domain_reliability or which mode/max_cost to pick for a given situation.

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