Changes since a previous extraction

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

No annotations are provided, so the description carries the full behavioral burden, and it does well: it enumerates the four result categories and states that modifications are field-level old -> new, specifically including price and dates. It does not cover edge behavior such as what happens when no snapshot exists at or before `since`, which is the notable remaining gap.

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 dense sentences with no filler, and the scope (arrival month) plus the baseline dependency are front-loaded. The trailing sentence fragment 'The start-of-month correction pass in one call' is a little cryptic but still short and informative.

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 and no annotations, the description must explain return semantics, and it does so by naming every change category and the old -> new granularity. Entities/companies filtering and the missing-snapshot error case are the only unaddressed pieces, so the definition is largely complete for a 4-parameter diff tool.

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 schema already documents all four parameters, and the description largely restates the `since` baseline semantics that the schema already defines. It adds arrival-month framing for `month` but says nothing about the `entity` and `company` filters, so it does not meaningfully exceed the schema baseline.

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 states the resource (bookings for an arrival month) and enumerates exactly what the call produces: new, modified, cancelled and disappeared bookings. It also anchors itself against the sibling get_bookings, whose snapshot is the comparison baseline, so an agent can distinguish it from get_booking/stays_in_month. It is slightly implicit about the verb (a diff/comparison), which keeps it from a 5.

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?

The closing phrase 'The start-of-month correction pass in one call' implies the intended scenario (month-start reconciliation), and naming get_bookings hints at the prerequisite of an existing snapshot. However, it never states the prerequisite explicitly (a prior extraction must exist) nor names when to prefer plain get_bookings or get_booking instead. Usage is implied rather than spelled out.

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