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

Annotations already declare readOnly, idempotent, non-destructive, and open-world hints. The description goes well beyond by disclosing that it returns edge_pp_net after slippage, Kelly fractions capped at 0.25, a 24h-move warning, caching behavior ('Cached 1h at KV level'), model-specific parameter details (e.g., per-sport alpha values, gate relaxations), and diagnostics for empty segments. This is rich behavioral context with no contradictions.

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 densely packed with necessary domain-specific information (model families, response fields, knobs, diagnostics). It front-loads the purpose and uses clear section markers (e.g., 'TRADEABLE-EDGE KNOBS'). Each sentence earns its place, though it could be slightly more scannable with breaks; still highly efficient given the complexity.

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, the description fully explains the return structure: by_segment, fed_candidates/fed_note, and _diagnostics with funnel counters. It also explains why segments may be empty, the meaning of each key field (edge_pp_net, kelly_fraction, liquidity, spread), and the Fed signal caveat. For a complex tool with 9 parameters and no output schema, this is exceptionally complete.

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% for all 9 parameters, so the baseline is 3. The description adds substantial extra meaning by explaining the role of tradeable-edge knobs (min_liquidity/max_spread_pp drop unrealizable edges), the special behavior of min_partition_leg_kelly (per-leg Kelly inside partitions, not parent level), and the subtlety that partition arbs always return kelly_fraction_half=0 at parent level. This compensates well beyond the schema.

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: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It clearly differentiates from sibling tools by emphasizing its three model families and 'what should I bet on today' use case, which is distinct from related Polymarket tools like polymarket_arbitrage or polymarket_edge_tracker.

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 states it is 'Built for "what should I bet on today"' and explains that agents discover opportunities without paging hundreds of markets. It provides context on when to use it (for tradeable-edge discovery) but does not explicitly name alternative sibling tools or state when not to use them. Clear context but no exclusions, matching a score of 4.

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