verify_step

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that output is limited to typed values (yes/no or closed set) to prevent instruction injection, discloses the measured accuracy (0.602 vs 0.569 baseline) and its advisory nature, and mentions the cost model (state x questions). This is exceptionally transparent about limitations and behavior.

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 concise yet information-dense. Every sentence adds value: purpose, output format, accuracy, advisory nature, and cost guidance are all packed into a compact paragraph. The most critical information (purpose and output type) is front-loaded, followed by performance and usage caveats. No filler or redundancy.

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 tool's complexity (5 parameters, no annotations, output schema present), the description is largely complete. It explains the core behavior, output format, accuracy, and usage constraints. It omits details on optional parameters, but these have defaults and are not critical for basic usage. The output schema exists, so return values need not be described. Overall, it covers what an agent needs to call the tool correctly, with minor gaps on optional settings.

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 0%, so the description must compensate. It clearly explains the two required parameters (before and after accessibility captures) by stating 'give the accessibility capture before and after the action'. However, it does not explain the optional parameters (backend, max_lines, timeout_ms), which remain undocumented. The description adds meaning for the core parameters but leaves the optional ones unexplained.

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 verb 'verify' and the resource 'a step from an accessibility diff', and explains the exact function: providing before/after captures and receiving typed answers about screen state. It distinguishes itself from sibling tools by focusing on verification rather than deciding, gating, or routing, and the specific input/output behavior is unambiguous.

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 usage guidance: treat answers as advisory evidence with a known error rate, never as the gate that decides a step is done. It also advises asking few questions per call due to encoder cost. This clearly tells the agent when and how to use the tool, and implicitly when not to (not as a gate).

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