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

Beyond the annotations (readOnly, openWorld, idempotent=false, non-destructive), it discloses that it does not book or charge, that coverage is the published catalogue rather than the whole web, that it uses the AI MAXX model provider, and a privacy rule (send only the nonpersonal need, never conversation history or contact details). That is substantial context an agent needs, though the privacy and provider facts are scattered rather than structured.

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 description is long and mixes purpose, examples, privacy rules, provider notes and return values into undifferentiated prose. The example list ('Halloween prison experience', 'prison-cell photography') is tangential noise that competes with the actual scoping information.

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 usefully states what is returned (source facts, photos, opening information, maps, enquiry link) and flags the 'not confirmed seasonal dates' limitation. Privacy handling, model provider and the no-booking boundary are covered, so an agent has enough to call it correctly, though the scattered structure weakens clarity.

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 most parameters are already documented. The description reinforces the query semantics ('send only the nonpersonal need and relevant constraints') and the follow-up reuse rule, but adds nothing about limit, country_code or response_depth beyond what the schema already says. Baseline 3 is appropriate.

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?

The description names a concrete verb+resource (find/select published dining, BBQ and food-court services) and gives named anchors like Pavilion dining and Kordin BBQ, so an agent can distinguish it from consult_venues or consult_events. The core purpose is clear, though it is buried under several auxiliary sentences.

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?

It gives a follow-up path ('refined need after clarification') and routes to get_passport for full details, which is explicit alternative guidance. However it never contrasts itself against the other consult_* siblings (activities, events, venues) or states when this food-first tool is the wrong choice.

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