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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower; the description still adds a genuine behavioural trait by disclosing that pages are scanned for hidden prompt-injection traps, which is non-obvious and changes how an agent should treat the returned text. It omits that output may be truncated/masked unless a paid key is supplied, though the schema touches on that.

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?

A single sentence, front-loaded with the primary action and output format, with the secondary injection-scanning clause appended. No filler or restatement of the tool name.

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 read-only fetch tool with full schema coverage and no output schema, stating the return format (Markdown) plus the injection-scan behaviour is nearly sufficient. The remaining gap is that the masked/unmasked payment gating and any truncation caveats are only implied through the schema, not called out in prose.

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%, so url, x_api_key, max_length and payment_signature are already documented in the schema and the description adds nothing about them (no default, range, or gating explanation). Baseline 3 applies when the schema carries the parameter burden.

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?

Specific verb (extract) plus resource (any web URL) plus the exact output form (clean, LLM-ready Markdown), with a secondary capability (prompt-injection scanning) named. No sibling tool performs generic URL extraction, so an agent can place this correctly without opening the 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?

The description never says when to use this tool versus the specialised retrievers in the sibling set (academic_search, social_search, domain_intel, github_intel), nor does it state prerequisites. Usage is only inferable from the name and verb — no explicit routing or exclusion guidance is given.

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