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

Annotations cover the safety profile (readOnly, non-destructive, open-world, non-idempotent), and the description goes well beyond them: discloses the AI MAXX provider, that coverage is the published catalogue rather than the whole web, that results are enquiries rather than confirmed dates, what is returned (facts, photos, opening info, maps, enquiry link), and a data-handling rule about not sending conversation history or contact details.

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?

Dense and front-loaded with the domain and examples first, then behavior and constraints. Every sentence carries information, though the example list and repeated caveats make it longer than strictly needed.

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?

No output schema exists, and the description compensates by describing the returned artefacts and next step. For an open-world, non-idempotent consultation tool, provider, coverage boundaries, data-handling rules and the no-booking caveat are all present, so an agent has everything needed to call it 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%, with query, country_code and response_depth already documented in the schema. The description adds meaningful semantics for the query parameter — it must be a nonpersonal need with constraints, and known constraints should be reused on follow-up — plus language handling and the instruction to respect the requested use. `limit` remains undocumented anywhere.

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?

Names a specific resource (venue hire, film/TV production spaces, historic prison photography) and the verb — interpreting a customer need and selecting relevant published services. It is clearly distinct from consult_activities/consult_events/consult_hospitality by domain, though it never explicitly contrasts itself with those siblings.

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 real usage context: send a direct or indirect customer need, follow up with a refined need after clarification, or use get_passport for full details, and states it does not book or charge. It stops short of explicit when-not-to-use routing against the other consult_* siblings.

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