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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral detail: it scans the latest large fills, evaluates wallet freshness, trade sizing relative to 24h volume, and extreme odds timing. The truncation slightly weakens disclosure of what each alert contains, but the detection logic is transparent.

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 single long, run-on sentence that is cut off mid-clause. While it packs useful information, it lacks structure and front-loading becomes less effective as the sentence unfolds. The truncation suggests poor quality control and makes the definition feel unfinished.

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?

Although an output schema exists and annotations cover safety, the description is incomplete due to truncation and does not mention how to specify custom values for min_usd or lookback_hours, nor what an 'alert' contains. The tool likely requires more guidance on input formatting and result interpretation, given its specialized detection logic.

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?

The schema's only parameter has 100% description coverage but only says 'parametros del producto (JSON o texto)', which is generic. The description compensates by revealing the expected keys: min_usd defaults to 10000 and lookback_hours defaults to 24. This tells an agent how to construct input even though the parameter is an unstructured JSON/text string.

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 opens with a specific verb and resource: 'Insider-style trade detection on Polymarket' and goes on to describe scanning large fills and flagging suspicious wallets. This clearly differentiates it from sibling tools like polymarket_whales or volume_anomaly. However, the description is truncated at 'Each alert car', which slightly obscures the final deliverable.

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?

The description implies when to use the tool by naming its insider-detection focus and giving default parameters (min_usd, lookback_hours). It does not explicitly state when not to use it or point to alternatives among the many related siblings. For an analyst, the use case is inferable but not directly routed.

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