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

Annotations already cover safety (readOnllyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds useful behavioral context: a configurable time window (default 7 days) and the meaning of the uma_risk flag (contested/undecided). It does not disclose data freshness, snapshot semantics, or pagination, and no contradiction exists between text and annotations.

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 purpose is front-loaded and the field list is information-dense. However, it reads as one run-on enumeration of eight fields and ends truncated mid-word ('resolu'), which is a structural defect in what the agent actually sees.

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 and annotations are rich, so return values and safety are largely covered. The description tells the agent what data it returns and the default window. The notable gaps are vague input semantics and no sibling-routing aid, though neither is fatal for a read-only watch 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 reported at 100%, so baseline is 3, but the schema description ('parametros del producto (JSON o texto)') is generic and offers minimal semantic value. The tool description compensates partially by revealing the default of 7 days and implying N is passed via the input, yet the expected JSON/text shape remains opaque.

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 specific verb and resource ('watch' + 'Polymarket markets ending within N days') and enumerates distinctive return fields: UMA resolution status, bond/reward, hours to resolution, price, volume, liquidity, uma_risk. This separates it from generic market tools. It stops short of naming close siblings like market_resolution or dispute_risk to differentiate, and the final sentence is truncated at 'avoid or exploit resolu'.

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?

No explicit when-to-use or when-not-to-use guidance appears. With 29 siblings including closely related tools (market_resolution, dispute_risk, resolution_verdict, resolution_source_feed), the agent must infer routing. The phrase 'Lets prediction agents avoid or exploit resolu[tion]' is only an implied use case, not a selection rule.

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