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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, and the description adds genuinely new behavioral context: the return payload shape (title, kind, page count, character count, truncation flag, text), the truncation behavior tied to maxChars, and the access model (no account, free hourly allowance, then an x402 reader pass). Rate-limit and auth disclosure is exactly the kind of information annotations cannot carry.

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 core capability leads the description and the practical details (return fields, maxChars cap, access terms) follow in a logical order with no filler sentences. The trailing "Served by readm3 (https://readm3.com/docs)" line is mildly promotional but provides a documentation pointer, so it is a minor rather than disqualifying inefficiency.

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, so the description carries the burden of explaining returns — and it does, listing the exact fields returned including the truncation indicator. Combined with format coverage, parameter caps and the access/pricing model, an agent has everything needed to call this correctly and interpret the response.

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 only 50% — the schema documents `url` but gives no description for `maxChars`. The description compensates by explaining maxChars' default (100,000), its ceiling (400,000) and that it caps the returned text, which is meaningful semantics beyond the bare maximum in the schema. The `url` parameter gains little beyond the schema's own "http(s) URL on the public internet" wording.

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?

The description states a specific verb and resource ("Fetch a document by URL and return its text") and enumerates the supported formats (PDF, web pages, Word, Excel, EPUB, Markdown, etc.), which is far more than a restatement of the name. An agent can immediately tell this is a URL-to-text extraction tool, distinct from any of the listed sibling readers.

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?

It gives concrete usage context — "Use it to summarize, quote or answer questions about a link" — which tells the agent what downstream tasks this tool feeds. There is no explicit when-not guidance or named alternative, but for a single-purpose reader tool with no close sibling, the stated context is sufficient to select it.

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