batch_evaluate

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

With no annotations present, the description carries the full burden of behavioral disclosure. It does reveal the core behavioral pattern (sequential navigation, uniform JS expression per page), but it does not disclose that arbitrary JS execution can have side effects or mutate page state, nor what the tool returns for each URL. For a tool that runs JavaScript across multiple pages, that safety-relevant gap is notable.

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?

Two sentences with zero filler: the first fronts the action (what the tool does), the second delivers routing guidance (when and when-not). Every clause earns its place.

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?

For a moderate-complexity tool with fully documented parameters, the description covers purpose and usage completely. The remaining gaps are the return format (no output schema exists to fill it) and unstated side-effect potential of JS evaluation (no annotations exist either). These are meaningful but do not prevent an agent from invoking the tool correctly.

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. The description reinforces evaluate_per_page's semantics ('the same JS expression on each') but adds no new parameter-level detail beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting.

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-resource-action combination: 'Visit several URLs in sequence and run the same JS expression on each.' It also explicitly distances itself from siblings by naming view_page/run_plan and stating what it is not for ('normal reading, clicking or form work'), making it impossible to confuse with the other browsing tools.

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 an explicit when-to-use condition ('controlled checks across known pages'), names the alternatives it replaces ('where view_page/run_plan would be too chatty'), and lists exclusions ('not for normal reading, clicking or form work'). An agent can make a correct routing decision with no additional inference.

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