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

No annotations exist, so the description carries the full burden and does: long-poll semantics, timedOut:true meaning nothing matched yet, empty timeouts not billed, dedupe on alert id, abandoned client calls lose nothing, and urgency (drops sell out in minutes). It also discloses trust semantics — confidence high vs low, title as untrusted third-party text, productUrl domain guarantee, kind values, and endedAt on sellout.

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 but front-loaded: the core wait/long-poll/loop contract comes first, then return shape, then trust guidance. It is long, and the confidence/title/productUrl/kind/endedAt passage reads as a block of field docs that could be tightened, but nearly every sentence carries operational weight.

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?

There is no output schema, and the description compensates by naming the return shape ({ alerts, cursor, timedOut }) and documenting the row fields an agent must interpret. For a 7-parameter polling tool with no annotations, nothing essential to correct invocation is missing.

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 100%, so the baseline is 3; the description adds real signal by explaining the cursor round-trip contract and the client-timeout constraint on timeoutSec, which the schema alone doesn't convey. It leaves maxMarkupPct and minConfidence largely to the schema, which already documents them well.

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?

States a specific verb and resource ("Wait for the next Pokemon TCG restock") plus the operational model (long-poll, stays open up to timeoutSec). It explicitly contrasts itself with set_webhook for the server-side case, so an agent can separate it from siblings without opening schemas.

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 explicit when-to-use (watch for a drop), how to use it (call in a loop, pass back the cursor each time so nothing is missed or repeated), and a concrete alternative (set_webhook for bots that shouldn't hold a connection). It even names the failure mode to avoid: keeping timeoutSec below the client's own tool-call timeout.

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