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

Annotations already declare idempotentHint=true and readOnlyHint=false, but the description adds substantive context those annotations lack: no prepaid fee, supplier permission gating, internal cost/frequency limits, live/test expiry, and the explicit caveat of 'No order, ticket or guaranteed fare.' That is meaningful behavioral disclosure beyond structured fields, though 'Never repeat an unknown request' adds ambiguity rather than clarity.

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 size is reasonable at four sentences and the dual-mode behavior is front-loaded. But the prose is dense and opaque ('ammo:use application', 'usage:read', 'live/test expiry conditions'), and the trailing 'Never repeat an unknown request' is an unexplained edict that reads as filler or warning without context.

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 a tool with five parameters, nested arrays, zero schema description coverage, and no output schema, the description should explain the request shape and what the queued task returns. It covers caveats well but omits all parameter meaning and the recovery-vs-queue decision criteria, leaving the agent unable to construct a correct call from the description alone.

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% across five parameters (slices, passengers, cabin_class, idempotency_key, max_connections), and the description compensates for almost none of it. The only implicit reference is idempotency via 'without a new query' and 'Never repeat an unknown request'; slices structure, passenger modeling, cabin_class enum, and connection limits are entirely undocumented. With low coverage this is a real gap.

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 resource (recorded flight response / bounded flight capability task), but the tool is called 'Search Flights' and the description never uses the word 'search' or clearly states that it finds flights. It splits into two jargon-laden modes ('ammo:use application', 'usage:read') and does not differentiate itself from siblings in the evuun_* family. An agent gets the gist but not a crisp verb+resource statement.

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?

There is conditional guidance: reuse the recorded response 'without a new query,' otherwise queue a task, and 'Never repeat an unknown request.' However, it never states when to prefer this over siblings like evuun_search_hotels or evuun_run_capability, and 'Poll its task with usage:read' references a scope, not a named tool. Usage is implied rather than explicit.

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