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

With no annotations provided, the description carries the full burden of behavioral disclosure. It is remarkably transparent about what the tool does: it aggregates trades, classifies wallets, detects specific signals (volume concentration, timing clusters with a precise threshold, volume spikes vs historical average), and returns a risk score with thresholds. It does not mention side effects, data freshness, or computational costs, but the algorithmic details go well beyond a generic 'analyze' and provide strong behavioral context.

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 three sentences, front-loaded with the primary purpose, and packs a substantial amount of detail without redundancy. Each clause adds value: the analysis methods, the specific signals, and the output format. There is zero waste, and the structure flows logically from purpose to methodology to results.

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?

Given the tool's complexity (multiple analyses, risk scoring, top lists) and the absence of an output schema, the description does a good job of explaining the return value (risk score with categories, triggered signals, top positioners/new wallets) and key parameter context. It does not explain interpretation of the risk score categories or limitations, but for a complex analytical tool, this is reasonably complete. The lack of explicit id/slug semantics is a minor gap.

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 50% (only max_pages and days_before_end have descriptions). The description adds the default window (7 days) and contextualizes days_before_end as the pre-event window, but it adds no explicit semantics for id or slug beyond the obvious 'market' context. It does not fully compensate for the missing schema descriptions, but the self-evident nature of id/slug and the context of 'Polymarket market' provide some support.

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: 'Analyze pre-resolution positioning on a Polymarket market.' It then enumerates distinct analyses (wallet aggregation, new wallet classification, volume concentration, timing clusters, volume spikes) and concrete outputs (risk score, top positioners). This clearly differentiates it from siblings like pg_position_timing_anomaly and pg_market_trades, which focus on narrower or different aspects.

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 does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions. The context implies it is for pre-resolution positioning analysis, but there is no 'use this when...' or 'for X use sibling' guidance. For a tool among many related siblings, this is a clear gap, though the specialized scope provides some implicit guidance.

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