ask

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

Annotations only declare readOnlyHint and openWorldHint; the description adds latency (~150-500 ms), cost (a fraction of a cent), the exact page data judged (URL, title, visible text, first open dialog, up to 20,000 chars), the TYPESAFE_API_KEY requirement and the failure contract ('any Jev problem is an error, never a default answer'). The closing 'reads the page without changing it' is slightly redundant with readOnlyHint but consistent with it.

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?

Single dense paragraph, front-loaded with purpose, cost and latency before the detail. Every sentence carries operational information, though the trailing 'It reads the page without changing it' restates readOnlyHint and is the one expendable clause.

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 3-parameter read-only judging tool with an output schema, this covers cost, latency, input scope, auth, error semantics and mode switching between yes/no and multi-option. An agent has everything needed to decide to call it and to construct valid 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 coverage is 100%, so baseline is 3; the description still adds real semantic content by explaining that omitting `options` yields a yes/no question returned as the probability of yes, and that supplying `options` returns a probability per option, with worked examples for both modes. It stops short of adding constraints on question phrasing beyond the single example, but the added value over the schema is genuine.

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 ('Ask the Jev decision model a question') and resource ('the session's active tab'), plus the output shape ('calibrated answer'). It distinguishes itself from siblings by naming evaluate and take_snapshot as the tools for counting, arithmetic and dates, so an agent can route without opening any schema.

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?

Gives explicit when-to-use contexts ('branching a script without a large model', 'checking a result after act') and explicit when-not-to plus alternatives ('weak at counting, arithmetic and dates, so ask those of evaluate or take_snapshot instead'). Nothing about selection is left to inference.

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