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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it states the tool 'fail-closed on invalid input', mentions the paid nature (~5 credits / $0.05) via prepaid key or x402, and notes that require_llm=true can cause processing failure if the LLM is unavailable. This is useful operational transparency that the annotations do not provide.

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: the first sentence states the core purpose, the second gives the when-to-use condition and sibling distinction, and the remaining sentences cover inputs, outputs, and cost/failure behavior. Every sentence earns its place, and the total length is appropriate for a tool with 5 parameters.

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?

The description is complete for an extraction tool with a rich schema and output schema. It covers the input constraint, the alternative tool, the output type, the fail-closed behavior, and the cost model. The output schema exists, so the description need not explain return values. Nothing an agent needs to call this tool correctly is missing.

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 description coverage is 100%, so the schema already documents all five parameters thoroughly. The description adds a small amount of extra meaning by summarizing the input constraint ('exactly one of text or html') and the optional nature of instruction/schema/require_llm, but it does not add significant detail beyond what the schema provides. Baseline 3 is appropriate.

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 ('Extract structured JSON') and resource ('messy plain text or HTML'), and explicitly distinguishes itself from extract.webpage by noting it is not for fetching a live URL. It also lists the kinds of fields it can extract (emails, phones, URLs, key-values, schema-shaped fields), making the tool's purpose immediately clear.

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 explicit when-to-use guidance: 'Call when the agent already has document text/HTML and needs machine-readable fields for the next step.' It also names the alternative (extract.webpage) and the condition that selects it ('not for fetching a live URL'). The input constraint 'exactly one of text or html' is also stated, which is critical for correct invocation.

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