Usage

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered externally. The description adds "real-time," which usefully signals data freshness rather than a cached snapshot, but it says nothing about authentication requirements, rate limits, or whether the figures are per-key or per-account.

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 with the substance front-loaded. The leading "Usage." merely restates the tool name and title, so there is a small amount of dead weight, but the rest is efficient.

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?

For a zero-parameter, read-only account-info tool with no output schema and full annotation coverage, the description states enough to call it correctly and anticipate what comes back. Only the freshness/scope caveats and sibling routing remain uncovered.

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 tool takes zero parameters, so the baseline is 4; the description correctly implies a purely account-scoped call requiring no input. Nothing further is needed or missing on the parameter front.

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?

"Retrieve real-time usage statistics and credit balance" names a specific verb and the two resources returned, which is clearly distinct from the sibling tools (get_endpoint, call_endpoint, search_endpoints) that deal with endpoints rather than account state. It stops short of explicitly stating that distinction, so it does not reach a 5.

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?

There is no guidance on when to call this versus the endpoint-focused siblings, and no mention of a pre-call check pattern (e.g., verifying credit balance before call_endpoint). The only contextual cue is "for your Piloterr account," which implies a no-argument account-scoped call but is not usage guidance.

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