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

The description goes far beyond the annotations (which already declare read-only, open-world, idempotent, non-destructive). It details critical behavioral aspects: snapshots are written on cache-miss, gaps mean no scan occurred, history depth is bounded by a 60-day TTL, and decay metrics are based on daily closes rather than intraday data. This enriches the agent's understanding of data reliability and limitations, adding significant value beyond the structured 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?

Despite being lengthy, the description is highly structured with clear sections (Args, RESPONSE, LIMITS) and uses bold/uppercase headers for readability. Every sentence carries substantive information: the opening question, parameter defaults, response shape with enumerated fields, and limitations. There is no redundancy or filler; the length is proportionate to the tool's 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 takes full responsibility for explaining the return value, and it does so in detail: tracked[] with full time-series and trend classification, expired[] with lifespan_days, and snapshot_dates[]. It also covers operational constraints (TTL, cache-miss gaps) and clarifies the meaning of negative edge values. This is a complete, self-contained explanation that enables correct invocation and interpretation.

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?

The input schema already covers both parameters with descriptions and defaults (100% coverage). The description adds meaningful context by framing 'window' as a 'snapshot family' (24hr | 1wk | 1mo), which clarifies the concept, and reinforces the days default and max. It also explains the response uses these parameters to pull time-series data. This is a moderate enhancement over the schema, justifying a score above the baseline.

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 the tool's function: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots' and poses the key question it answers: 'how long has this edge existed and is it shrinking?'. This distinguishes it from sibling tools like polymarket_edges (which likely generates current edges) by focusing on historical persistence, and from polymarket_arbitrage by targeting edge decay rather than spread analysis.

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 implies when to use: to differentiate between a fresh wide edge and a 3-week-old wide edge, suggesting it's for evaluating whether an edge is still viable. It also mentions 'the median lifespan is your competition clock', providing practical context. However, it does not explicitly name alternative tools or state when NOT to use this tool, so it falls short of full exclusionary guidance.

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