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

The description goes well beyond the annotations, which only declare read-only, open-world, idempotent, and non-destructive. It discloses data gaps ('snapshots are written when polymarket_edges runs on a cache-miss'), historical limits ('60-day snapshot TTL'), and computational methodology ('decay numbers come from daily closes of edge_pp_net (net of default slippage), not intraday'). It also explains the signed meaning of edge_pp_net, providing significant behavioral insight.

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 fairly long but every section earns its place: purpose, argument recap, detailed response format, and data limitations. It is front-loaded with the core purpose and then systematically explains the output. Slightly dense, but well-organized and not verbose.

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 tool's complexity (time-series edge tracking with computed trends and decay) and the absence of an output schema, the description fully compensates by detailing the response structure (tracked[], expired[], snapshot_dates[]), the meaning of each field, and the inherent data limitations. It provides a complete mental model of what the tool returns and how to interpret it.

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% with descriptions for both parameters. The description repeats the defaults and adds minimal context like the term 'snapshot family' for window, but this is not substantially beyond what the schema already provides. It does not clarify parameter formatting or edge cases beyond the schema, so it meets the baseline but does not elevate it.

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 specific purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots' and answers a precise question about edge longevity and decay. It distinguishes itself from the sibling polymarket_edges by focusing on time-series persistence rather than just current edges, explicitly contrasting fresh versus old wide edges.

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 strong usage context: it explains what question the tool answers ('how long has this edge existed and is it shrinking?') and gives a practical example of when it should be used (comparing a fresh wide edge to a 3-week-old one). It does not explicitly name alternative tools like 'use polymarket_edges for current edges,' but the context implies this distinction clearly enough.

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