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

Annotations already mark the tool as readOnly, idempotent, and non-destructive, which the description complements rather than repeats. The description discloses rich behavioral detail: it 'walks the ladder,' returns specific fields like top_of_book and vwap_fill_price, interprets size_usd differently for buys vs sells and basket notional, and explicitly warns about partial-fill directional risk. No contradiction with 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 description is dense but exceptionally well-structured, with explicit CAPS section markers (REQUIRES, SINGLE-MARKET, BASKET, USE THIS) and a front-loaded purpose. Every sentence provides either a constraint, a return field, or rationale, and no content is redundant or filler. It earns its length by covering a complex tool with two modes in a scannable format.

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?

With no output schema to lean on, the description fully enumerates return fields for both modes (e.g., top_of_book, vwap_fill_price, slippage_pp, verdict, thin_legs[], max_clean_notional_usd, forced_directional_risk), explains size_usd semantics, and highlights the key risk scenario (partial fills turning an arb into directional exposure). This is complete for an advisor/check tool, giving the agent all necessary context to invoke and interpret results.

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 meaningful semantics beyond the schema by stating the exclusivity constraint ('REQUIRES one of market or event') and clarifying mode-dependent behavior for size_usd (max spend vs target proceeds vs settlement notional). It also explains default behavior for basket side auto-selection, which enriches parameter understanding.

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, informative purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes between single-market and basket modes, lists return attributes, and explicitly ties usage to sibling tools ('USE THIS before acting on any polymarket_arbitrage... or any polymarket_edges trade above ~$500'), making it unmistakable what the tool does and how it differs from similar tools.

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 explicitly states when to use the tool ('USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500') and explains why ('theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position'). It also provides mode-specific input requirements and a warning about the dominant loss mode, offering strong guidance beyond mere existence.

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