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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial non-obvious behavioral context beyond these: snapshots are written on cache-miss (explaining gaps), history depth is bounded by a 60-day TTL, and decay numbers are based on daily closes of edge_pp_net 'net of default slippage, not intraday.' This is exactly the kind of operational nuance that helps an agent reason about results.

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 the average tool description but is clearly structured into sections (the core question, Args, RESPONSE, LIMITS). Every segment carries useful information: the response format is critical because there is no output schema, and the limits section directly influences interpretation. It could be slightly tightened, but it earns its length.

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?

With no output schema, the description fully specifies the response structure: tracked[] with the full time-series, first_seen, trend, and decay_pp_per_day; expired[] with lifespan_days; snapshot_dates[] and what gaps mean. It also covers the TTL bound and data source caveats. For a tool of this complexity, the description is remarkably 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?

The input schema already covers both parameters with descriptions (days: 'Lookback in days (default 14, clamp 2-30)', window: 'Which polymarket_edges window family to read snapshots for: 24hr | 1wk | 1mo (default 1wk)'). The description repeats these arguments nearly verbatim, adding only the phrase 'snapshot family' and a note on the lookback maximum. Since schema coverage is 100%, the baseline is 3; the description adds marginal interpretive value but no new parameter-level semantics.

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 specific verb and resource: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It clearly answers a question ('how long has this edge existed and is it shrinking?') and distinguishes itself from sibling tools like polymarket_edges (which presumably provides raw current edges) by focusing on historical persistence and decay.

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 states a clear use case: 'Answers "how long has this edge existed and is it shrinking?"' and elaborates with examples (fresh vs. 3-week-old edge). It implies when to use it for decay analysis, though it doesn't explicitly name alternative tools or state when not to use it. The contrast with the newest snapshot and expired opportunities gives practical context for interpretation.

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