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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond them: availability is up to 5 minutes stale, more than 10 matches return the best 5, totalMatchesAtLeast signals partial checking, refinements and notes are returned, and a used default for guests is reported. It even discloses that no result is ranked by payment, which is useful trust context.

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?

Front-loaded with purpose, then parameters, then return shape, with no filler sentences. It is dense for a single paragraph and interleaves input and output details, which slightly hurts scannability, but every clause carries information an agent needs.

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 fully carries the return contract: propertyId, name, city, state, sleeps, bedrooms, bathrooms, averageNightlyRate, plus returned, totalMatches/totalMatchesAtLeast, nextCursor, refinements and notes. For a 12-parameter search tool this is complete enough to call correctly on the first attempt.

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 100%, so the baseline is 3, but the description adds real meaning: sort=fit is defined as smallest unit that sleeps the party, then bedrooms, then name; amenities must ALL be listed; guests default and its reporting; and averageNightlyRate is scoped to per night over the stay before cleaning fee and taxes. It does not elaborate on limit/cursor interplay, which keeps it from a 5.

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 and resource ('Lists the units on one Booking Bench site that can be booked for a stay') and immediately scopes it by availability rules and guest capacity. It is clearly distinguishable from get_property (single unit), list_sites (sites, not units) and get_quote (live pricing), so an agent can select it without opening the schema.

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 concrete usage context: checkIn and checkOut are required, guests defaults to 2, and it names the optional filters and sort options. It also routes the agent to get_quote when live availability/pricing is needed, but it does not explicitly state when to prefer get_property or list_sites instead.

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