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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), yet the description still adds genuinely non-obvious behavior: the credit cost ('Costs 3 API credits per call'), the permission tiers gating filter features, the pagination ceiling relative to the caller's predictions.max_results with omitted limit counted as 20, and the default PnL ordering. These are operational facts an agent cannot get from the schema or 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 resource name is front-loaded, followed by permissions, then pagination, then return shape, then cost — a sensible ordering. The middle sentence ('Open/closed tabs and event expansion remain available in default PnL order') is slightly opaque and the paragraph is dense, but no sentence is redundant.

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 carries the burden of explaining returns and does so at the right granularity ('one row per outcome token, with volume, value, buy/sell totals, PnL, shares, and resolution status'), and it covers auth, cost, and pagination limits. It stops short of describing the response envelope or whether pagination metadata is returned, which is a minor gap for a paginated list tool.

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?

The nested query schema is already richly documented (descriptions, examples, defaults, min/max), but the two top-level parameters have no descriptions and the reported coverage is 0%. The description compensates by grouping parameter families ('search, market/token filters, numeric bounds and sorting') and, more importantly, by stating a cross-parameter constraint the schema does not encode: offset + limit may not exceed predictions.max_results.

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 names a concrete resource and scope: 'Returns every market a trade address has traded — one row per outcome token', which tells an agent the unit of the result (market/outcome token) rather than just restating the tool name. It does not, however, distinguish itself from the many other Polymarket siblings (GetPolymarketPositions, GetPolymarketActivity, GetPolymarketWalletEventHistory), so an agent must infer the boundary itself.

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?

Usage context is present but framed as prerequisites rather than selection guidance: 'Requires predictions.read and either predictions.explorer or predictions.filter. Additional search, market/token filters, numeric bounds and sorting require predictions.filter.' That tells the agent what it can do, but never says when to choose this tool over a sibling Polymarket tool or what it excludes.

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