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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the bar is lower, yet the description still adds substantial behavior: tri-state filter semantics, the rule that unknown values are excluded when a filter is set, the contents of each result (verified_facts with source URL and date, record page, booking_link), and a licensing/citation obligation. This is well beyond what the annotations convey.

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 the trigger and coverage before filters, output and examples, and nearly every sentence earns its place. The single dense paragraph is long for a 12-parameter tool and repeats the Grandvalira village list that the area parameter already implies, so it would benefit from light structuring.

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?

There is no output schema, but the description still describes the return payload (verified_facts, record page, booking_link) and the absence of prices/photos/availability. Combined with coverage limits, filter semantics and the citation requirement, an agent has everything needed to call and interpret this tool correctly.

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%, and the description compensates for the remainder with meaning the schema cannot carry: 'true = the official website explicitly says so; false = it explicitly says no; properties with unknown values are excluded', plus definitions for min_stars ('category stated on the official site') and the Grandvalira alias expanding to five villages. This is real semantic value, not restatement.

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 (search) and resource (hotels in Andorra) with a precisely bounded scope: three named parishes plus Grandvalira. An agent can immediately tell this is the hotel-specific search rather than the generic search_entities. It stops short of 5 because it never names the sibling tools it should be preferred over.

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?

Opens with an explicit when-to-use trigger ('Use this when a user asks for accommodation in Andorra') backed by five concrete example queries, and closes with explicit when-not guidance ('No prices, photos or availability'). The agent knows both the entry condition and the limits of the tool before calling it.

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