well-006-url-metadata

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the bar is low, yet the description goes well beyond them: $0.005 USDC x402 charge, 1 MB body cap, ~10s timeout, 5-redirect limit, scheme/private-IP rejection, and a 'nothing is stored' statement. These are exactly the operational facts an agent needs before spending money or hitting a timeout.

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?

Front-loaded with purpose, then constraints, then return shape — a good information hierarchy in four dense sentences. The 'Provided as is, with no warranty or guarantee of accuracy or fitness' clause is boilerplate that consumes space without helping an agent decide or call the tool.

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 carries the return contract and does so explicitly, enumerating { url, final_url, content_type, title?, description?, canonical?, lang?, open_graph, twitter, warnings }. Combined with the cost, size, and timeout limits, an agent has everything needed to invoke this tool correctly.

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 100% for the single 'url' parameter, so the schema already documents the type and the https/rejection constraint. The description restates the same scheme rejections in the opening sentence but adds no syntax, encoding, or normalization detail beyond it — the baseline 3 applies when the schema does the heavy lifting.

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 https URL') plus the concrete operation ('extract HTML head metadata'). It even names the payment mechanism, so an agent knows exactly what this tool does without opening the schema. No siblings exist to differentiate from, so nothing further is required.

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 clear operating context through hard constraints — https only, rejection of http/file/data/localhost/private IPs, and the paid-request cost — which effectively tells the agent when this tool is applicable. It stops short of explicit when-not-to-use guidance (e.g. for non-HTML content or authenticated pages), but with no sibling tools there is little routing ambiguity to resolve.

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