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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral detail: snapshots are written on cache-miss so gaps indicate no scan, history is bounded by a 60-day TTL, decay is computed from daily closes not intraday, and edge_pp_net is signed (negative means SELL YES). It also warns that expired opportunities may be closed/resolved/arbed away. No contradiction with annotations.

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 well-organized with labeled sections (Args, RESPONSE, LIMITS) and packs in essential operational details. It is longer than average but every sentence contributes either behavioral context or output/limitation info. A minor deduction for the slightly verbose explanatory asides ('wide for a reason nobody is willing to take') that are illustrative but not strictly necessary.

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 that there is no output schema, the description fully explains the response structure: tracked[] with time-series, trend categories, decay metrics; expired[] with lifespan; and snapshot_dates[] semantics. It also covers data gaps and TTL limits. This is a complete picture for an agent to select and invoke the tool correctly, even though the tool is relatively complex.

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 repeats the parameter defaults ('default 14, max 30', 'default 1wk') already present in the schema. It adds slight context by calling 'window' a 'snapshot family' and noting days limit, but this is minimal beyond structured schema coverage. No significant additional semantic value is provided.

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 function: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It explicitly answers 'how long has this edge existed and is it shrinking?' and differentiates its temporal scope from the likely current-edge tool 'polymarket_edges' by emphasizing snapshot history. The verb 'track' and resource 'edge persistence/decay' are specific and unambiguous.

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 usage context: it explains that a fresh wide edge and a 3-week-old wide edge are distinct trading situations, implying when historical persistence matters. It also describes the snapshot mechanism and gaps, helping the agent reason about data availability. However, it does not explicitly name sibling tools as alternatives (e.g., 'use polymarket_edges for current edges'), so it falls short of a 5.

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