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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the burden is low; the description nonetheless adds substantial behavior: pricing semantics with vs without dates, that totalCents matches get_quote, result ordering with bookable places first, and the from-price-per-night fallback. These are outcome-shaping facts an agent cannot get from annotations or schema.

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 dense sentences, front-loaded with the scope constraint and then the pricing behavior; each sentence carries information an agent needs. The middle sentences are long and clause-heavy, which costs a little readability without adding waste.

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 read-only, 8-parameter search with no output schema, the description covers the important return facts (totalCents, from-price, bookable flag, ordering) and the collection-resolution path. It omits pagination/result-count behavior and any mention of the filtering parameters (amenities, minBedrooms), which leaves a small gap an agent may have to probe for.

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 3. The description adds real meaning for `collection` (slug origin, posadita.com/s/{slug}, /llms.txt) and for the date pair (pricing behavior), but says nothing about minBedrooms, propertyType, availableOnly, or the all-of-not-any amenity semantics — the latter is only carried by the schema.

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 ('Search ONE collection – a host's portfolio, a residential community or a destination') and explicitly bounds the scope with 'There is no search across all of Posadita.' That boundary alone lets an agent distinguish it from sibling tools like get_property and check_availability without opening any 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 clear conditional usage: with dates and guests every place is priced for that stay and bookable ones sort first; without dates you get from-prices. It also names the downstream gate ('Only places with bookable:true can be quoted or checked out') and names get_quote as the equivalent figure. It stops short of an explicit 'use X instead when Y' routing statement for get_property/check_availability.

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