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

With no annotations, the description carries the burden well: it declares read-only, discloses the 5000-row scan ceiling when filters are applied, and names has_more/total_matched so the agent understands truncation. It stops short of describing permissions or the row shape itself.

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?

Four short sentences, front-loaded with what the tool returns, then filters, then guardrails. No filler or restated title.

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 and no annotations, the description supplies ordering, truncation semantics and return signals, which is enough to call it correctly. Minor gaps: no mention of default page size or whether offset beyond the scan window behaves differently.

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?

Adds real meaning beyond the 60%-covered schema, notably that a date-only `to` is inclusive and that from/to/type/pagination are the filters. The pagination caveat about has_more/total_matched also contextualizes limit/offset, which have no schema descriptions.

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?

Names the resource precisely (credit deductions + grants of the workspace) and the ordering (newest first), which separates it from aggregate siblings like get_credit_usage_by_type or get_balance. It never names those siblings explicitly, so differentiation is inferred rather than stated.

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?

States that filters are optional and explains the consequence of using them (scan of newest 5000 rows), which implies this is the raw-ledger listing tool. There is no explicit guidance about when to prefer it over the usage-aggregation or balance siblings.

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