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

The description discloses several behavioral traits beyond annotations: it is a paid operation (500 micro-dollar credits), requires prior preparation via agent_utilities_prepare, and has billing implications for new requestIds. It also clarifies it does not submit or return field values, which aligns with idempotentHint=true and adds context about side effects (none destructive). No contradiction with 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?

The description is three sentences, with the core purpose front-loaded, followed by billing, prerequisites, and recovery guidance. Every sentence adds necessary operational context, with no filler or repetition. The structure is efficient and easy to parse.

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 covers the tool's scope (30 forms), prerequisites (prepare, credits, auth), billing model, and idempotency/recovery behavior. With an output schema present, return-value details are not needed. The description is complete for an agent to know how to call it correctly, including the critical 'first use prepare' instruction.

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?

The schema already documents requestId and maxPriceMicroUsd with descriptions, and the description adds context about recovery and billing for those. However, the input object (html, baseUrl) is not described in the schema, and the description only indirectly references html by mentioning 'forms.' baseUrl is left unexplained, so the description only partially compensates for the missing schema coverage (67%).

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's function: 'Describe up to 30 forms and their controls without returning field values or submitting anything.' This gives a specific verb (describe), resource (forms and controls), a scope limit (30), and explicitly excludes actions (no field values, no submit). It also distinguishes from sibling tools like html_links or html_headings by focusing on forms.

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 provides explicit prerequisites: 'First use agent_utilities_prepare for this tool' and notes it requires existing credits and a private Authorization header. It also explains recovery behavior via requestId reuse. However, it does not contrast this tool with alternative html_* tools (e.g., when to choose forms over links), so it lacks a direct 'when-not' clause.

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