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

The description discloses extensive behavioral details beyond annotations: caching (1h at KV level), three model families with their exact formulas and models, tradeable-edge knobs, output structure including diagnostics for empty segments, and a '24h-move warning' when edge may already be priced in. Annotations only indicate read-only, open-world, idempotent, and non-destructive—this description adds substantial operational 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 lengthy but well-structured with numbered segments, bold terms, and clear delineation of model families and knobs. Every sentence adds unique information, though the density may be high for some agents. It is front-loaded with the primary use case and model families.

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 complexity (9 parameters, no output schema, multiple segments), the description is highly complete: it explains the response top-level structure (by_segment, fed_candidates, diagnostics) and caching behavior. It lacks an explicit JSON output example but covers the key fields. With no output schema, the burden is high, but the description handles it well.

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% but the description adds significant value beyond basic schema descriptions—e.g., explaining the relationship between min_kelly and min_partition_leg_kelly, providing default values with reasoning (slippage_pp default 0.3 with context on Polymarket spreads), and offering practical tuning guidance (bump/ drop for thin partitions).

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 clearly states it scans Polymarket markets and returns opportunities where Pipeworx data disagrees with market price, with the explicit use case 'what should I bet on today'. It distinguishes from siblings like polymarket_arbitrage and polymarket_edge_tracker by focusing on edge detection from model families.

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 provides explicit use context ('discover opportunities without paging hundreds of markets') and explains the three segments and when each applies. It also notes that Fed bets are excluded from ranking due to unreliable signal, offering guidance on limitations. It does not explicitly state when not to use it versus alternatives, but the context is clear.

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