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

Annotations already establish readOnlyHint, idempotentHint and non-destructive behavior, and the description adds real context beyond them: data provenance (provider vs manual), the fact that some sources expose no grant totals at all, the multi-currency `base_*` USD convention, and the immutability of provider-sourced credits. These are genuinely useful behavioral disclosures for interpreting results.

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 purpose and scope lead the paragraph, with caveats (budgets ignore credits, currency check, source semantics) following in a logical order. It is one dense run-on sentence chain, so a few clauses could be trimmed or broken out, but essentially every sentence adds 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 no output schema, the description carries the full burden of describing return values and does so: balances, burn rate, projected exhaustion, per-source readability, currency and source fields. It also covers the important gotcha that credit figures differ from budget/spend figures.

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 schema already carries no semantics to compensate for; the description instead explains response fields (balance, burn rate, projected exhaustion, `source`, `currency`). No parameter meaning is left ambiguous.

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 specific verb and resource ("List this account's credits") and immediately scopes what counts as a credit: provider-read AWS Activate/promotional grants plus hand-entered ones for sources like GCP. It also names the backing endpoint (GET /api/accounts/:accountId/credits), which distinguishes it unambiguously from siblings such as list_budgets or query_costs.

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 frames the tool as "presentation and forecast only" and warns that budgets, spend limits and anomaly detection count gross spend and ignore credits, which tells the agent when not to expect credit data elsewhere. It also routes removal to the sibling delete_credit and restricts it to manual credits. It stops short of an explicit when-to-prefer-this-over-alternatives statement, keeping it below a 5.

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