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

Annotations already indicate read-only, idempotent, non-destructive safety. The description adds substantial behavioral context: snapshot write-trigger conditions (cache-miss), gaps meaning no scan, 60-day TTL, and that decay is computed from daily closes rather than intraday. It also explains the signed nature of edge_pp_net and what negative values mean, providing valuable transparency beyond annotation hints.

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 structured with clear sections (purpose, Args, RESPONSE, LIMITS) and every sentence adds value. It packs detailed information without wasted words, making it dense but readable. The front-loading of the core question and the organized response format make it easy to parse.

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, trends, decay, historical gaps) and the absence of an output schema, the description is remarkably complete. It enumerates response fields (tracked[], expired[], snapshot_dates[]), explains their semantics, and discloses important limitations (TTL, daily-only decay). No critical aspect seems missing.

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% and includes defaults and ranges for both parameters. The description reinforces these details and adds interpretative context: 'days' is a lookback and 'window' selects the snapshot family, with examples of valid values. This helps the agent understand how parameters influence the returned time-series, going slightly beyond raw 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 states a specific purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It answers a clear question ('how long has this edge existed and is it shrinking?') and distinguishes itself from the sibling polymarket_edges tool by focusing on time-series persistence and decay rather than current 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 a clear use case: comparing fresh vs. old edges and understanding decay. It implies when to use this tool (when persistence/decay matters) but does not explicitly name alternatives or say when not to use it. The relationship to polymarket_edges is mentioned, which orients the user, but explicit exclusions or sibling comparisons are absent.

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