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

Annotations already declare readOnly/openWorld/non-destructive, but the description adds real behavioral context beyond them: it is AI-model-backed, its coverage is limited to the published catalogue rather than the whole web, it cannot book or charge, and it imposes a privacy constraint on what may be sent. That is meaningful disclosure for an LLM-backed tool.

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?

Purpose is front-loaded in the first clause, and the privacy/scope caveats close it out efficiently. The example list ('Halloween prison experience', 'prison-cell photography') is slightly decorative but does clarify the domain and breadth of acceptable 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 compensates by summarizing returns (source facts, photos, opening info, maps, enquiry link) and by covering privacy, iteration, and non-booking behavior. The main remaining gap is alternative-selection guidance against the consult_* siblings.

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% (only 'limit' lacks a description), so baseline is 3. The description adds genuine meaning by stating what the query must and must not contain (nonpersonal need plus constraints, never conversation history or contact details) and that constraints should be reused on follow-up, which is not in 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?

Specific verb+resource: interprets a customer need and selects relevant published services, with complementary options. It clearly distinguishes itself from get_passport (full details) and states the scope is the published catalogue. It does not differentiate against the consult_activities/consult_events/consult_venues/consult_hospitality siblings, which appear closely related.

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?

Explicit about when it applies ('enquiries for relevant existing services, not confirmed seasonal event dates') and how to iterate ('follow up with a refined need after clarification') with a named alternative (get_passport). It also states the tool does not book or charge. It gives no routing guidance versus the vertical consult_* siblings, so it falls short of a 5.

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