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

Annotations already declare read-only, idempotent, non-destructive hints. The description goes far beyond that by disclosing cache-miss snapshot writes, the 60-day snapshot TTL, decay computation from daily closes of edge_pp_net (net of slippage), and the signed nature of edge values (negative = SELL YES). This provides significant behavioral context absent from annotations. No contradiction.

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 typical but every sentence delivers essential information. It is structured with clear labels (Args, RESPONSE, LIMITS) and an upfront purpose statement. There is no fluff, repetition, or vague language; the word count is justified by the complexity of the tool's behavior.

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 lacking an output schema, the description explicitly details the response structure (tracked[], expired[], snapshot_dates[]) with field names and semantics, explains limiting conditions (snapshot TTL, cache-miss gaps, history start point), and describes how trend/decay metrics are computed. This makes the tool's behavior fully predictable without needing extra documentation.

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%, with both days and window having descriptive text. The description restates these definitions and adds the term 'snapshot family,' but this is essentially a synonym for what the schema already says. Since the schema carries the full load, the description adds no critical semantic value beyond the baseline.

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 tracking edge persistence and decay over time from daily polymarket_edges snapshots, answering a specific question: 'how long has this edge existed and is it shrinking?' This distinguishes it from sibling tools like polymarket_edges (current edges) and polymarket_arbitrage. The verb 'track' and the explicit research question give a precise scope.

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 about when the tool is valuable (e.g., a fresh wide edge vs. a 3-week-old wide edge represent different trade opportunities) and explains data availability limitations (snapshot gaps, TTL). However, it does not explicitly name alternatives or state when not to use the tool, though sibling names implicitly draw the contrast.

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