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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds crucial behavioral details: history is bounded by a 60-day TTL, snapshots are written on cache-miss so gaps mean no scan, decay uses daily closes not intraday, values are signed (negative = SELL YES), and trend classifications are enumerated. This is exactly the kind of non-obvious behavior an agent needs to know.

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 well-structured and dense. It front-loads the purpose, then uses clear labels (Args, RESPONSE, LIMITS) to organize parameter, output, and limitation details. Every sentence adds value, no fluff or repetition.

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 thoroughly explains the response shape: tracked[], expired[], and snapshot_dates[] with their fields and semantics. It also covers data pipeline quirks (cache-miss snapshots, TTL) and calculation methodology. This is unusually complete for a tool with simple inputs.

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 coverage is 100%, so the description has little to add. It restates defaults (days default 14, max 30; window default '1wk') which are already in the schema. It does add a small amount of context by calling window a 'snapshot family' and mentioning the 24hr|1wk|1mo options, but this largely duplicates schema descriptions. Baseline 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 states the tool's purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots' and answers a specific question ('how long has this edge existed and is it shrinking?'). It uses a specific verb+resource ('tracker' for edge persistence) and naturally distinguishes itself from siblings like polymarket_edges by focusing on historical edge decay over time.

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?

It gives practical usage context: a fresh wide edge and a 3-week-old wide edge are 'different trades,' implying this tool is for assessing edge age/decay. It also tells the user how to interpret results ('the median lifespan is your competition clock'). It does not explicitly name alternative tools, but the sibling context and domain are clear enough.

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