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

Annotations already declare openWorld=true, idempotentHint=true, destructiveHint=false and readOnlyHint=false. The description adds genuinely useful context beyond them: the operation is asynchronous ('Queue ... Recover its actual task with usage:read'), free, subject to source permission and cost/frequency limits, and caching-aware. But 'usage:read' and 'ammo:use' are unexplained jargon, and no return/latency behavior is described.

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 a dense, jargon-saturated run-on where the key fact (an asynchronous queued hotel search) is buried. Terms like 'ammo:use' and 'MoR conditions' consume space without adding usable signal, and there is no front-loaded statement of what the tool does.

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 8-parameter, required-all, no-output-schema, mutation-adjacent tool, the description does address async execution, idempotency, permissions and safety exclusions. Still missing: how results are retrieved in concrete terms, and any coverage of currency/guest_nationality/idempotency_key semantics, leaving real gaps for correct invocation.

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 0%, so the description must carry parameter meaning. It alludes to 'actual country/city/dates/occupancy' (mapping loosely to country_code, city, checkin/checkout, occupancies) but adds no format or semantics, and leaves currency, guest_nationality, and idempotency_key entirely undocumented in both schema and description.

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 frames this as queuing a 'free non-booking hotel capability task' and explicitly excludes prebook/payment/booking, which distinguishes it from booking flows. But the core verb+resource ('search hotels') is obscured by opaque jargon like 'ammo:use' and 'usage:read', so an agent must infer the real purpose from the title rather than the text.

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 negative guidance ('No prebook, payment, booking or repeated unknown request') and notes cached responses do not start a new query, which is useful routing context. However, it never names the alternative siblings (e.g., evuun_prepare_hotel_inquiry, evuun_search_flights) or states the positive condition for choosing this tool.

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