web.trace

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

No annotations exist, so the description bears the full burden. It does disclose the shape of the output (natural-language stage trace plus statistics, mirroring the dashboard), which is real value since there is no output schema, but it says nothing about whether the call is read-only, whether it re-runs a live query or replays recorded telemetry, cost/latency, or paging.

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 short sentences, output described first, purpose second — well front-loaded with no filler. The parenthetical 'what the dashboard draws' is slightly cryptic and the whole definition is terse to the point of under-specification, but nothing is wasted.

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 tool with three undocumented parameters, no annotations, and no output schema, the description is far too thin; an agent cannot tell what 'top' or 'urls' do or when to prefer this over web.stats. Only the output content is covered.

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% across three parameters (required 'query', plus 'top' and 'urls'), and the description explains none of them. 'top' and 'urls' are completely opaque from both schema and prose, so the description fails to compensate for the coverage gap.

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 resource: a full natural-language trace of pipeline stages plus statistics, framed as a debugging view of 'what happened'. That is more concrete than a restated name, though it never positions itself against the nearby web.stats or web.drift_report, which also surface pipeline data.

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 one implied trigger ('for debugging what happened') but names no alternatives and no exclusions (e.g., use web.stats for aggregate metrics only, use web.trace when you need stage-by-stage narrative). An agent must infer the boundary from sibling names alone.

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