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

Annotations already indicate a safe, idempotent read operation (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false). The description adds substantial behavioral context beyond these: snapshot writes occur only on cache-miss, gaps in snapshot_dates mean no scan occurred, history is bounded by a 60-day TTL, and decay numbers come from daily closes of edge_pp_net rather than intraday data. This fully details the tool's behavior and limitations without contradicting 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?

The description is dense and well-organized into labeled sections (RESPONSE:, LIMITS:). It packs a lot of necessary information (response fields, interpretation, data caveats) without fluff. While it is longer than a typical description, every sentence contributes functional value, and the structure aids scanning. Not a 5 because it could be slightly tightened, but it is far from 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?

Despite having no output schema, the description thoroughly explains the response structure: tracked[] entries with time-series, first_seen, trend, decay_pp_per_day; expired[] with lifespan_days; and snapshot_dates[] with the cache-miss caveat. Limitations such as the 60-day TTL and daily-close basis are covered. Given the tool's analytical nature, this description provides complete context for an agent to understand inputs, outputs, and edge cases.

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 clear descriptions for both days and window. The description goes further by explaining the default lookback (14, max 30), the snapshot family concept, and the response context (e.g., days is the lookback, window determines which snapshot series is read). This adds practical meaning beyond the schema's basic descriptions, so it earns 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 begins with a specific purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It directly answers the core question ('how long has this edge existed and is it shrinking?') and distinguishes itself from the sibling polymarket_edges by focusing on historical persistence rather than current edge values. The term 'tracker' plus the detailed explanation make the tool's function unmistakable.

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 clear usage context: it is for assessing edge persistence and decay, with a concrete example comparing fresh vs. 3-week-old edges. It explains that expired opportunities reveal the competition clock. However, it does not explicitly name alternative tools for when to use something else (e.g., polymarket_edges for current snapshots only) or state when not to use this tool, so it falls short of full alternatives guidance.

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