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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, but the description adds valuable context beyond them: the call is free, refunds are only available when the raise fails its minimum, and it exposes partial unlock state that changes over time. These are exact behavioral expectations an agent needs.

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 front-loaded with the action and embedded with a clear field list and a useful workflow note. Some field enumeration overlaps with what an output schema would provide, but the detail is relevant and clearly organized.

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 an output schema exists, this description covers the key behavioral context: monitoring role, refund conditions, and the trigger for switching to claim_ilo_tokens. Missing details are the no-pledge edge case and how the agent learns the cliff/release window, but those gaps are minor.

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?

With 0% schema description coverage, the description compensates fairly well by tying the meaning of launch_id and wallet_address to 'a launch' and 'this wallet' and by introducing the per-wallet cap that the allocation logic depends on. It does not explicitly describe caller_id or provide ID/wallet formats, which keeps it from a 5.

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?

Opening with 'Read your own on-chain Pledge record for a launch' gives a specific verb, resource, and scope. The returned fields—pledge amount, share, cap headroom, pro-rata allocation, release schedule, refund availability—make the tool's purpose concrete and distinct from related ILO/claim siblings.

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 'Workflow: MONITOR step' sentence tells the agent to poll this between cliff and full release in order to decide when a claim_ilo_tokens call is worth making. That gives clear usage context and names the relevant alternative, though it doesn't explicitly enumerate when to prefer other read-only siblings.

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