alethia_eval

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

With annotations present (readOnlyHint: false, destructiveHint: false), the description adds meaningful context: it runs in the navigated page rather than the host UI and returns the evaluation result. However, it does not explicitly warn that arbitrary JS may have side effects, though this is partially implied by readOnlyHint: false.

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?

Three concise sentences deliver the core purpose, execution context, and usage guidance without redundancy. Information is front-loaded and every sentence 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?

Given the tool's simplicity (one parameter, no output schema) and strong annotations, the description covers purpose, context, examples, and execution environment. It is fully complete for an agent to select and invoke 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 coverage is 100% and the only parameter 'expression' is well-defined with an example. The description adds usage examples but does not add new parameter-level semantics beyond what the schema already provides, warranting the baseline score.

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 evaluates a JavaScript expression in the page under test, using the specific verb 'Evaluate' and identifying the resource. It distinguishes itself from siblings by emphasizing the page context versus the Alethia host UI and positions itself for queries the NLP compiler cannot express.

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?

Explicitly says 'Use this for queries the NLP compiler cannot express' and provides concrete examples (counting elements, reading computed styles, checking localStorage). It also implicitly excludes use for host UI operations and anything the NLP compiler can handle, giving clear when-to-use and when-not-to-use guidance.

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