web.eval

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

No annotations exist, so the description carries the full burden and does not meet it. It does not say whether live mode performs network calls, whether the gate verdict can fail/block a pipeline, what happens when thresholds are unmet, or whether the call is expensive or long-running.

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?

A single short sentence with no fluff, but it is terse to the point of under-specification, and the parenthetical mode list is doing work that belongs in prose. There is nothing to cut, but also little structure to front-load information beyond the two mode names.

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?

With three parameters (one nested), no annotations, no output schema, and zero parameter documentation, an agent cannot determine what the tool returns or how to construct thresholds. The definition is far from complete for a tool whose output apparently includes a pass/fail gate verdict.

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 glosses 'mode' (replay/live) and implies 'gate' triggers a verdict, but 'thresholds' is a nested object with completely undocumented shape and keys in both schema and description.

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 names an activity (quality evaluation) with two modes (offline replay / live) plus an optional regression-gate verdict, which is more than a restatement of the name. However, 'jakość' (quality) of what is never specified — pages, search results, or answers — and nothing distinguishes it from siblings like web.verify_links or web.drift_report, both of which also assess output quality.

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?

No indication of when to pick this over web.verify_links, web.drift_report, or web.stats, nor when replay vs live mode is appropriate. The parenthetical mode names hint at a choice but give no selection criteria.

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