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

The description adds significant behavioral context beyond the annotations. It discloses that 'snapshots are written when polymarket_edges runs on a cache-miss, so gaps mean nobody scanned that day,' that history depth is bounded by the '60-day snapshot TTL,' and that decay numbers 'come from daily closes of edge_pp_net, not intraday.' These details help the agent interpret data gaps and time-series correctly. No contradiction with annotations (readOnlyHint=true, destructiveHint=false).

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 average but heavily information-dense. It is structured with 'Args', 'RESPONSE', and 'LIMITS' sections, making it easy to parse. Every sentence provides useful detail; there is no fluff or repetition. The length is justified by the absence of an output schema, which requires the response structure to be described inline.

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 carries the full burden of explaining return values. It does so thoroughly: tracked[] with fields (full edge_pp_net time-series, first_seen, trend, decay_pp_per_day), expired[] with lifespan_days, and snapshot_dates[]. It also explains limitations (TTL, cache-miss gaps, daily closes) which are critical for correct interpretation. For a read-only telemetry tool with two simple params, this is fully 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?

Schema description coverage is 100%, so the baseline is 3. The description's Args section ('days (lookback, default 14, max 30), window (snapshot family, default "1wk")') mostly repeats the schema, but adds the phrase 'snapshot family' which clarifies that the window parameter selects between families of snapshots (24hr vs 1wk vs 1mo), reinforcing the schema's 'window family' phrasing. This is marginal value beyond the schema.

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 uses a specific verb (track) and distinct resource (historical edge snapshots), and differentiates from the related polymarket_edges tool by focusing on how edges persist and decay over time. The phrase 'Answers "how long has this edge existed and is it shrinking?"' ties it to a concrete use case.

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 context on when to use it: 'a fresh wide edge and a 3-week-old wide edge are different trades' implies this tool is for historical persistence analysis. However, it does not explicitly name an alternative tool or state 'use this instead of polymarket_edges'; the guidance is implicit rather than explicit. The mention of 'daily polymarket_edges snapshots' indirectly points to the relationship with the sibling tool.

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