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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral context about cost and payment ('Paid: $0.50–$1.50 per call from your Einstein credit balance') and the availability of free alternatives. It doesn't go into rate limits or response format, but with strong annotations this is sufficient.

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 a single, information-dense sentence that front-loads the primary purpose ('Polymarket analysis') and then lists the five analysis modes. The payment note is bracketed and separate, keeping the main description clean. No redundant wording or fluff.

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?

The description covers the core functionality, cost, and alternatives, which is strong for a complex tool with no output schema. However, it does not specify what the response looks like (e.g., a summary report, data table, or narrative insights) or any pagination/format details for the results. Given the tool's multiple modes, a brief note on output type would make it fully complete, but the current description is still adequate.

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 schema provides basic descriptions for 'kind' (enum values listed) and 'limit'/'query' with ranges. However, the tool description enriches the enum semantics by explaining what each kind does (e.g., 'scan for insider-shaped positions' corresponds to 'insiders', 'measure bid/ask spreads' to 'spread'). This adds meaning beyond the bare enum list, compensating for the schema's nominal coverage.

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 performs Polymarket analysis and enumerates five specific actions ('browse live markets, scan for insider-shaped positions, measure bid/ask spreads, find high-conviction positioning, or fade over-priced long shots'). These map directly to the 'kind' parameter, distinguishing it from more specialized sibling tools like get_prediction_market_catalysts or get_polymarket_whales by its multi-purpose analysis capability.

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 explicitly includes cost and alternative guidance: 'Paid: $0.50–$1.50 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.' This tells the agent when to use this tool (when the user is willing to pay) and directs to a sibling tool for free alternatives. It also implies usage per analysis type, e.g., if the user asks for bid/ask spreads, this is the appropriate tool.

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