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

Annotations only cover the safety profile (readOnly, openWorld, non-idempotent, non-destructive); the description adds the facts an agent actually needs to decide: USD 0.003 per call, payment via x402 with USDC on Base, and that failed calls are free. Pricing and payment prerequisites are exactly the kind of context annotations cannot carry, and the non-idempotent hint is consistent with a paid per-call operation.

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 well-front-loaded sentence that leads with the action and input forms, then appends limits, options, and cost. Every clause carries information, though the packed pricing/payment tail makes the sentence dense enough to be worth splitting.

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?

No output schema exists, yet the description still conveys the essentials: model, length options, focus, size cap, and the billing model. The missing piece is that neither text nor url is required in the schema and the description never states that one must be provided, leaving a real chance of a no-input call.

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% (text and length have no schema descriptions), but the description compensates: it caps text at 60,000 characters, enumerates short/medium/long for length, and clarifies that focus is an optional topic and URL must be public http(s) pointing at a page or PDF. The one remaining gap is the mutual relationship between text and url.

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 (summarize) plus the exact input modalities — raw text up to 60,000 characters, or a public web page/PDF by URL — and names the model and length options. An agent can immediately distinguish this from siblings like read_url, url_to_markdown, or file_to_markdown, which convert rather than condense.

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 clear operating context: two input paths (text or URL), a hard 60,000-character limit, optional topic focus, and three length settings. It stops short of explicit routing against siblings (e.g., when to prefer url_to_markdown) and doesn't say that at least one of text/url must be supplied, since the schema marks nothing required.

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