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

Annotations already declare readOnly/idempotent/destructive, but the description adds significant behavioral depth beyond those hints. It explains how snapshots are written (on cache-miss), why gaps occur, the 60-day TTL bound, and that decay numbers come from daily closes 'not intraday.' It also clarifies the signed meaning of edge_pp_net and the trend classification logic. This is rich, actionable context that annotations alone do not provide.

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 longer than average but every sentence earns its place. It is structured into Purpose, Args, RESPONSE, and LIMITS sections, making it scannable despite the density. The front-loaded purpose sentence immediately conveys the essence, and the later sections provide necessary detail. It is appropriately sized for a telemetry tool with nuanced interpretation; a shorter description would lose critical context.

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?

Without an output schema, the description fully compensates by detailing the response shape: tracked[] with fields, expired[] with lifespan_days, and snapshot_dates[]. It also covers limitations (TTL, snapshot enabling, daily closes) and edge cases (gaps meaning no scan). For a tool with such complexity, this is complete and self-contained.

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 covers 100% of parameters with descriptions including defaults and clamps. The description adds complementary semantics: it calls 'window' a 'snapshot family' and reinforces the lookback default and max. This adds conceptual meaning (snapshot family implies grouping across time) beyond the schema's raw value descriptions, so a score above baseline is warranted.

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 noun phrase: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It then states the exact question it answers ('how long has this edge existed and is it shrinking?'), which clearly distinguishes it from sibling tools like polymarket_edges that likely provide current edge values. The purpose is specific and immediately recognizable.

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 explains when to use the tool by framing the problem: 'a fresh wide edge and a 3-week-old wide edge are different trades (the latter is wide for a reason nobody is willing to take).' It also gives context about snapshot gaps and TTL limits. While it doesn't explicitly name alternative tools, the implied contrast with snapshot creation and the 'daily polymarket_edges' reference make it clear this is for historical persistence rather than current edges.

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