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

With no annotations, the description carries the full behavioral burden and does the hardest part: it discloses that this is a paid operation ($0.02 USDC on Base) and, critically, that the MCP call does NOT return extraction results but payment requirements. That non-obvious two-step semantic is exactly the kind of thing an agent would otherwise get wrong. It omits failure modes, expiry of payment requirements, and whether results are returned on the settle path.

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?

Two dense sentences, with the most decision-relevant fact (this costs money) front-loaded before the mechanics. Nothing is wasted and it can be read in a few seconds.

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, and the description compensates by explaining what actually comes back over MCP (payment requirements) and how to complete the transaction. Combined with the paid nature of the call, this covers what an agent must know before invoking. Minor gaps remain around error handling and whether the settled POST returns the extracted JSON directly.

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 0% and the schema object is a free-form nested object, so the description has to carry meaning. It does explain the role of each parameter – the URL is the source, the JSON schema defines the desired output structure – which the bare schema does not convey. It gives no detail on supported JSON-schema subset, nesting depth, or format constraints.

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 transformation: a URL plus a JSON schema becomes structured JSON, which is a clear verb+resource statement. It is distinguishable from siblings like scrape_markdown and check_url, though it never names those siblings to draw the contrast explicitly.

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 second sentence explains the payment flow (MCP call returns requirements, settle via POST /v1/extract), which is useful operational guidance. However, there is no statement of when to choose this over scrape_markdown for schema-driven extraction versus plain markdown scraping, and no prerequisites or exclusions beyond the payment step.

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