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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so safety is covered. The description adds real behavioral context beyond that: the figures are live totals rather than an estimated window, which tells the agent results are not scoped by query. It says nothing about freshness latency, currency, or whether totals include pending holds waiting on release.

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?

Two short sentences, front-loaded with the returned categories before the scoping caveat. No filler; each sentence carries information. Slightly compressed to the point that the period sentence reads ambiguously.

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 usefully names the three earning states an agent will receive, which is the minimum needed to trust the result. However, the unresolved tension between the offered 'period' parameter and the claim that no custom period is applied leaves a real gap for a zero-required-parameter read 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?

Schema description coverage is 0%, so the description must carry the one parameter, and it does so only by negation: 'A custom period is not applied.' That leaves the agent unsure whether 'period' is honored, ignored, or rejected, and gives no format guidance (maxLength 40 with no documented syntax). The statement adds uncertainty rather than semantics.

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 specific resource (expert earnings) and enumerates the exact breakdown returned: pending, releasable, and paid. It clearly contrasts with an estimate over a window by stating the figures are live totals. It does not differentiate itself from closely related siblings such as get_releasable_balance, get_wallet_balance, or list_payouts.

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 is only implied: an agent can infer this is the right tool for a snapshot of lifetime earnings totals rather than a period report. There is no explicit statement of when to prefer get_releasable_balance or get_wallet_balance, nor any prerequisites. The one exclusion offered ('a custom period is not applied') is about the period argument, not about choosing between tools.

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