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

Annotations already declare the safe read profile (readOnly, idempotent, non-destructive, non-open-world). The description adds real behavioral context beyond them: partial totals only include priced groups, unpriced guests and unsupported origins are reported separately, and it interprets the urlRestoresEstimate field. That is substantive disclosure the structured fields do not carry.

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?

Four tightly-packed sentences, front-loaded with what is estimated and in what currency. Each sentence carries distinct information (currency, partial-total behavior, link-restore field, non-live caveat), so little is wasted, though the density is on the high side.

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 no output schema, the description must cover return semantics, and it does: partial totals, separately reported unpriced guests, and the meaning of urlRestoresEstimate. The main remaining gap is that it never explains the shape of the returned link or units/per-guest breakdown.

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 100%, so the baseline is 3. The description rises above it by clarifying that origins must be supported US metros (implying some cities return no price) and by noting unpriced/unsupported inputs are reported separately, which explains the semantics of the `groups`/`city` input in the result.

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 (estimates) and resource (round-trip flights and typical-stay lodging in USD for guest groups), clearly distinguishing it from siblings like get_budget_estimate or get_alcohol_estimate by domain. It never names an alternative sibling, so sibling differentiation is implied rather than explicit.

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?

Usage is implied through scope constraints (supported US metros, supported destination slugs) and the caveat that estimates are not live fares or bookings. There is no explicit when-to-use vs. when-not-to-use guidance or routing to a related estimator tool.

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