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

Annotations already mark it read-only, open-world, idempotent, and non-destructive. The description goes well beyond annotations by disclosing concrete behavioral traits: snapshots are written only on cache-miss so gaps mean no scan, history is bounded by a 60-day TTL, decay is computed from daily closes of edge_pp_net net of default slippage rather than intraday, and expired opportunities are those gone from the latest snapshot. No contradiction exists.

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 densely informative and well-structured into purpose, arguments, response shape, and limits. Every clause carries operational value, such as the sign convention for edge_pp_net, the median lifespan as a competition clock, and snapshot date gaps. This is not padding; 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?

There is no output schema, so the description fully carries the burden of explaining return values. It defines tracked[], expired[], snapshot_dates[], explains trend and decay fields, clarifies the sign of edge_pp_net, and covers edge cases like gaps and TTL. For a two-parameter, read-only tool, this is complete enough for correct invocation and interpretation.

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 description coverage is 100%, so the input schema already documents both days and window. The description adds only mild context: days is the lookback with default/max, and window refers to the polymarket_edges window family. This does not meaningfully exceed the schema's explanations, so the baseline of 3 is appropriate.

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 identifies the tool as 'edge persistence and decay telemetry' built from daily polymarket_edges snapshots and explicitly frames the question it answers: 'how long has this edge existed and is it shrinking?' This is specific and distinguishes it from the sibling polymarket_edges tool, which presumably provides current edge data rather than historical tracking.

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 does not explicitly say 'use this instead of X', but it strongly implies when this tool is appropriate: for historical edge persistence and decay analysis across snapshot history, whereas polymarket_edges would be the current-edge sibling. It also sets expectations with limits like the 60-day TTL and snapshot-gap behavior, giving an agent enough context to select it correctly.

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