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

Even with readOnlyHint, idempotentHint, and destructiveHint already present, the description adds substantial behavioral context: it walks the order-book ladder, returns a detailed field set, interprets size_usd differently per mode, and explicitly warns 'FEES ARE NOT MODELLED HERE' with gross vs net distinction. It also discloses failure modes such as partial basket fills creating unhedged directional positions.

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 long, but it is densely organized with clear mode labels (SINGLE-MARKET, BASKET) and every sentence adds operational information. The core purpose is front-loaded, followed by requirements, mode-specific behavior, and critical caveats, with no filler or repetition.

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, two modes, and absence of an output schema, the description is remarkably complete. It enumerates all key return fields per mode, states the market-or-event requirement, explains size_usd semantics, names the dominant loss mode, and flags the unmodeled fee so the agent can compensate via polymarket_edges/fees.ts.

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?

While schema coverage is 100%, the description meaningfully extends parameter meaning beyond the schema. It explains that market selects single-market mode and event selects basket mode, defines size_usd as 'max spend on buys, target proceeds on sells' in single-market and 'settlement notional S' in basket mode, and clarifies side defaults and auto-selection behavior.

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 precise statement of purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly identifies the resource (Polymarket order books), the verb (check), and distinguishes two operating modes (single-market and basket), which separates it from sibling tools like polymarket_arbitrage and polymarket_edges.

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 gives an explicit when-to-use directive: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains why it matters in that context ('theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position'), giving the agent clear decision criteria.

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