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

Annotations only declare readOnlyHint and openWorldHint, and the description layers on genuinely useful behavior beyond them: rate limits (1 per IP per UTC day, 20 shared ASN, 20 global), a monetization model (limited free result plus paid upgrade links), and auth context (x402 payment via Apify, no account needed). That is exactly the rate-limit/auth context the 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?

Tight, front-loaded sentences: purpose first, then exclusions, then the cost/limit facts. Every clause is functional — nothing is padding, and the payment details are unusual but decision-relevant.

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?

With no output schema, the description usefully states what comes back ('a limited free result and paid upgrade links'). Combined with rate limits and payment model, an agent has enough to call it correctly, though return-shape specifics (e.g. how extracted fields are keyed) are left unstated.

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 50%: 'url' is documented in the schema, while 'fields' has no description though it does carry minItems/maxItems constraints. The description alludes to the 'fields' concept ('Extracts named fields') but does not explain the 1-5 limit or expected field-name format, so it only partially compensates for the coverage gap — baseline 3 is appropriate.

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?

Names a specific verb+resource+mechanism ('Extracts named fields from one public page with AI'), which clearly differentiates it from generic fetch/read siblings like read_url or smart_fetch. It scopes the operation ('one url') but never names a concrete sibling alternative to help disambiguation, so it stops just short of a 5.

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?

Provides explicit exclusion guidance: 'Use for one url. Not for batch work or unrestricted monitoring,' which rules out the tempting misuse cases. It gives clear context but no named alternatives (e.g. which tool handles batch or article body extraction), so it is not a full 5.

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