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

Annotations declare readOnly, idempotent, and not destructive. The description adds rich behavioral context: it returns time-series (edge_pp_net across snapshots), trend classification (new/widening/stable/decaying), decay rate, expired opportunities with lifespan, and snapshot dates. It also discloses that snapshots are written on cache-miss and that decay is based on daily closes not intraday. This fully characterizes behavior beyond 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 long but efficiently structured: purpose sentence, key question, response breakdown in bullet-like format (tracked[], expired[], snapshot_dates[]), and limits. Every sentence adds value; no redundancy. It is front-loaded with the core mission and ends with important caveats.

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 no output schema, the description fully specifies the return structure (arrays with fields and their meanings). It explains edge_pp_net sign convention, first_seen, trend classification, decay_pp_per_day, expiration with lifespan_days, and snapshot dates. It also covers limitations (60-day TTL, non-intraday decay). For a tool with two optional parameters, this is 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?

Both parameters have schema descriptions (100% coverage). The description adds meaning by explaining 'days' as lookback (default 14, max 30) and 'window' as snapshot family (24hr|1wk|1mo). It clarifies that snapshots exist only for days when polymarket_edges ran on a cache-miss, which is crucial for interpreting the 'days' parameter. This enriches the schema definitions.

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 purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It answers the specific question 'how long has this edge existed and is it shrinking?' and distinguishes itself from sibling tools like polymarket_edges by focusing on time-series persistence rather than current snapshots.

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 explicitly advises when to use this tool over alternatives: 'a fresh wide edge and a 3-week-old wide edge are different trades' implies it should be used when edge age and trend matter. It also provides context on snapshot gaps and history TTL, helping agents decide if the data is appropriate. While it doesn't list specific 'when not to use' conditions, the contrast with raw edge data is clear.

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