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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, but the description adds real behavioral depth beyond them: the member vs non-member vs former-member payment rules, the requirement of a live signed per_verified_task cover, and the exact failure mode (409 payout_not_covered with its payload). That is material context an agent cannot get from the annotations or schema.

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 core question is front-loaded, followed by return shape, eligibility rules, error behavior, and a call to action. Compact brace notation keeps the payload details short, and every sentence carries information; nothing is padding.

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 correctly spells out the four returned fields and the error contract, plus the edge cases (non-member, member, former member). It is nearly complete, though it does not say what happens when amount is zero/invalid or whether results are cached.

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 baseline is 3, and the description goes beyond it by tying the three parameters into a meaningful relationship — company pays agent a USDC amount — and by echoing them in the error payload. It adds semantic framing rather than raw format detail.

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 frames a precise predicate — 'Would the company be allowed to pay this agent this amount for a task?' — with a named resource (payout cover) and even the exact return shape {covered, member, membership_id, max_per_task_usdc}. An agent can immediately distinguish this read-only pre-flight check from action-oriented siblings like verify_task or resolve_task.

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?

'Run it before assigning paid work' gives a clear when-to-use trigger, and the 409 payout_not_covered consequence explains why the check matters. It never names an alternative tool or an explicit when-not-to-use condition, so it falls short of the top band.

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