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

It discloses important behavioral traits beyond annotations: it is a paid operation costing 300 micro-dollar credits, requires a private Authorization header, and a new requestId creates a new billable operation. These details align with idempotentHint=true and add significant context about side effects and recovery.

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 compact and front-loaded: purpose first, then billing, prerequisites, and recovery guidance. Every sentence adds necessary operational information with no fluff.

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 output schema exists, the description does not need to explain return values. It covers the main operational requirements, but it leaves baseUrl semantics unexplained and does not clarify how the Authorization header is supplied, making it slightly incomplete for fully independent 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 coverage is 67% with requestId and maxPriceMicroUsd already described. The description reinforces requestId semantics by linking it to agent_utilities_prepare and mentions recovery, but it does not explain the html input or baseUrl parameter beyond the schema. This is adequate but not exceptional.

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 clearly states the tool discovers up to 50 RSS, Atom and JSON Feed links from supplied HTML, using a specific verb and resource. This distinguishes it from sibling tools like html_links and html_metadata.

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 usage context: first call agent_utilities_prepare, requires credits and an Authorization header, and reuse prepared arguments for recovery. It does not explicitly name alternative tools or state when not to use it, but the prerequisite and billing guidance is strong.

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