Wait briefly for a SpicyAPI task

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: adaptive backoff 'from about 2 to at most 10 seconds,' that an explicit intervalSeconds 'stays fixed,' and crucially that 'a local wait timeout does not cancel the task.' That last point is exactly the kind of side-effect disclosure an agent needs and is not inferable from the schema.

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 core action is front-loaded and each sentence carries distinct payload (backoff, webhooks, timeout semantics, text/transcript output, layer stacking). It is a dense single paragraph with no wasted sentences, though the layer-decomposition detail makes it slightly packed for quick scanning.

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?

An output schema exists, yet the description still usefully explains output shapes (assets[].url, output.text, output.transcript, per-layer assets). Safety is covered by annotations. It does not address failure/error states or what a task that never completes returns, leaving a minor gap for a long-running polling tool.

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 only 33% (only intervalSeconds is documented), so the description must compensate. It does: 'up to 300 seconds' maps to the timeoutSeconds maximum and the backoff-vs-fixed-interval sentence adds meaning beyond the schema's terse intervalSeconds note. taskId is self-evident, so the coverage gap is largely filled.

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 states a specific verb+resource+scope: 'Wait for a task for up to 300 seconds and read ready output.assets[].url directly.' It also implicitly differentiates from the one-shot sibling by naming the polling behavior and noting that a verified webhook 'needs no extra task_get,' so an agent can tell this apart from spicyapi_task_get.

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 real routing context: 'Prefer signed webhooks for production' steers the agent away from polling when a callback exists, and the task_get remark clarifies the polling path. It stops short of an explicit 'use this when you must block vs. use task_get for a single status check' statement, so it is clear but not fully explicit about the sibling alternative.

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