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

Annotations already declare readOnly, openWorld, and non-idempotent, but the description adds substantial behavioral detail: clutter removal, blocking of private/internal addresses, size (2 MB) and timeout (10 s) limits, no charge on rejection, and pricing model. This goes well beyond structured annotations.

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?

The description is front-loaded with core function and key constraints, and mostly earns its place. Some phrases ('Built for AI agents that need to read the web', 'In the free trial') are slightly promotional, but overall efficient.

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?

Given the simple input (one required URL), existing output schema, and annotations, the description provides all necessary context: what it returns, key limitations, cost, and safety boundaries. No critical information is missing for correct invocation.

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 the single parameter is fully documented in the schema. The description adds only a brief example ('Pass the page address as url: https://...'), which is helpful but minimal beyond the schema's existing explanation.

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 (fetch) and resource (public web page) along with the exact output format (clean Markdown, page title, all links as JSON). It implicitly distinguishes itself from sibling extract-json by emphasizing Markdown+links rather than structured JSON extraction.

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 gives a general context ('Built for AI agents that need to read the web') but does not explicitly say when to use this tool versus alternatives like extract-json, crawl, or search. No when-not guidance beyond blocked private/internal addresses.

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