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

Goes well past the readOnly/idempotent/openWorld annotations: discloses the bucketing methodology (first 60s of unique buyers, buy SOL, dev buy), shrinkage toward coarser buckets under thin samples, a 6-hour rebuild cadence that implies staleness, pricing ($0.01/call, 10 free/day, x402 payment-required result), and error semantics (isError with message, not charged). This is unusually rich operational context.

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?

Front-loaded with the core answer and method, then cleanly segmented into 'When to use', 'Price', and 'Errors'. The opening sentence is clause-heavy (em-dash aside plus a secondary explanation), but nearly every sentence carries decision-relevant information.

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 an output schema present the description need not describe return shapes, and it doesn't try to. It covers everything an agent needs to select and invoke correctly: methodology, refresh cadence, cost, error behavior, and the boundary against the sibling that bundles this check.

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% and the single 'mint' parameter is fully documented in the schema, including base58 format and length constraints. The description adds no parameter-level detail beyond what the schema already conveys, so the baseline of 3 applies.

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?

Opens with a precise verb+resource+scope: the probability that a specific pump.fun launch graduates, computed empirically from comparable historical launches and expressed as a lift over the ~3% base rate. This is clearly distinguishable from siblings like pump_token, pump_launches, and pump_pulse, which the agent can rule out without opening any schema.

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?

Explicitly bounds itself: 'For graduation probability only', then names the alternative (launch_scan on the A.U.G.U.R Synapse · Wallets & Risk server) and clarifies that the sibling bundles this check with others. It also states the cost model and free tier, which is a real selection factor.

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