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

Adds substantial behavioral disclosure beyond annotations: per-call cost (500 micro-dollar credits), the prepare-first prerequisite, credit and Authorization-header requirements, and the billing semantics of reused vs new requestId (recovery vs new billable operation). This fleshes out what idempotentHint=true means in practice and is consistent with all annotations.

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?

Five short sentences, each carrying distinct information: purpose, price, prerequisite, auth, and recovery semantics. The core purpose is front-loaded, and there is no filler or restatement of what the schema already says.

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 an output schema present and two of three parameters well documented in the schema itself, the description covers the non-obvious operational facts an agent must know: cost, prerequisite step, auth requirements, and recovery semantics. Minor gaps remain around behavior on insufficient credit and error handling beyond 'reuse prepared arguments.'

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 already documents requestId and maxPriceMicroUsd well (67% coverage); the description adds the workflow meaning — that requestId originates from agent_utilities_prepare and that reusing versus generating a new requestId controls billing. The html parameter lacks an explicit description, but its purpose is reasonably implied by 'source table cells.'

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 and resource — 'extract source table cells' — and adds a distinguishing behavioral detail, 'without expanding spans.' This clearly separates it from sibling HTML tools (html_forms, html_headings, html_links, html_main_text) without needing to open their schemas. No ambiguity about what this tool does.

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?

Provides explicit procedural context: first use agent_utilities_prepare, requires existing credits and a private Authorization header, and explains what counts as a new billable operation. This is actionable guidance, though it does not name alternatives or exclusion conditions relative to the sibling html_* tools.

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