Booking MCP

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

With no annotations, the description carries the full burden and does substantial work: it discloses the experimental/scraped provenance, the WAF blocking failure mode, that fields are null when Booking omits them, and that results may be cached (via no_cache). It does not mention rate limits, cache TTL, or what the 'blocked error' looks like, which keeps it below a 5.

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?

The EXPERIMENTAL warning and the sibling routing are correctly front-loaded, which is the right priority. However, the two full result-shape enumerations duplicate the output schema that already exists, and that block occupies roughly half the description without adding information an agent doesn't already have structurally.

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 an experimental scraper with 8 parameters and no annotations, the description supplies everything needed to call it correctly and to interpret a failure: provenance, blocking risk, the fallback tool, nullability of fields, and cache bypass. Return values are covered by an output schema, so the extra shape listing is redundant rather than missing.

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 all 8 parameters including limit, currency, rooms/adults, and no_cache are already documented in the schema. The description adds no parameter-level meaning beyond that (it discusses output fields instead), so the baseline 3 applies.

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 ('hotels on Booking.com') scoped to a location and stay window, and enumerates the fields returned per property. It also explicitly contrasts itself with the named alternative google_hotels_search, so an agent can route without opening either 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 a concrete condition for preferring the alternative: Booking sits behind AWS WAF and this call may return a blocked error, while google_hotels_search is 'the reliable alternative'. It stops short of an explicit 'prefer that tool by default' instruction or guidance on retry behavior, so it is clear context rather than a full when/when-not rule set.

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