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

Annotations already carry readOnly/idempotent/non-destructive, so this description does not need to restate safety. It adds genuinely non-obvious behavior beyond them: results are range-based with explicit assumptions and caveats, and the tool deliberately excludes latency and Core Web Vitals forecasting. It does not describe how the dollar figure behaves when the cost parameter is omitted beyond the schema's brief note.

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 tight sentences: purpose first, scope limits second, input sourcing third. Every sentence contributes, though the sourcing sentence is dense and packs multiple clauses that could be slightly cleaner. No filler or repetition.

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 an output schema present, the description need not explain return values, and it correctly focuses on caveats and inputs instead. For a four-parameter read-only estimator the coverage is strong; the minor gap is that the effect of the default browser cache rate on results is not discussed.

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 75%, so the baseline is near 3, but the description adds real meaning: it explains that bandwidthCostPerGbUsd is optional and only enables the dollar calculation, and it supplies provenance for unpkgBytesPerPageLoad via audit_dependencies. Only monthlyPageViews remains entirely unexplained, and its meaning is self-evident.

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 opens with a specific verb and resource: an order-of-magnitude estimate of bandwidth offloaded and hosting dollars when bytes move from first-party hosting to UNPKG. It also distinguishes itself from the sibling audit_dependencies by naming that tool as the upstream source of one input, so an agent can tell the two apart without opening schemas.

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?

It states the context in which the tool applies (bytes moving to UNPKG, optional $/GB to include dollars) and explicitly bounds when not to rely on it: it cannot forecast latency or Core Web Vitals. It also prescribes how to obtain the key input from audit_dependencies' impact.convertNowEntryBytes. What it lacks is a named alternative for scenarios where a range estimate is insufficient.

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