Usage history

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely useful context beyond them: deterministic newest-first ordering and the fact that the call is free, which saves an agent from cost anxiety. It does not state pagination/total-count behavior, but given the annotation coverage this is solidly above baseline.

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?

A single compact sentence with the resource and ordering front-loaded, followed by a field inventory and a one-word cost note. No filler or repetition, and each clause carries information an agent would otherwise have to discover by calling the tool.

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 does the necessary work of enumerating returned fields and their ordering, which is exactly what an agent needs to decide whether this tool answers its question. Minor gaps remain around result caps and how filters combine, but nothing essential for correct invocation is missing.

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 75% and the description never references any of the four parameters by name; 'days', 'limit', 'offset', and 'market' filtering are documented only in the schema. 'Newest first' is the only hint relevant to pagination, and 'market that served' only loosely relates to the market filter, so almost nothing is added beyond the schema.

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?

States a specific resource with scope: per-request (not aggregate) history of the account, ordered newest first, and enumerates the fields returned (model, provider pseudonym, tokens, cost, market, routing reason, latency, savings). That contrasts implicitly with aggregate siblings like carpe_usage_summary, though no sibling is named explicitly, which keeps it from 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 explicit when-to-use guidance, no exclusion of alternatives, and no prerequisites. With 31 sibling tools including carpe_usage_summary, carpe_key_usage, and carpe_routing_summary, an agent is left to infer from the phrase 'per-request history' that this is the detail-level view rather than the aggregate one.

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