llm_usage

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

No annotations are provided, so the description carries the full burden. It describes what the tool shows but does not disclose behavioral traits such as read-only access, side effects, data aggregation process, or authentication requirements. The description adds minimal behavioral context beyond stating it is a dashboard.

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 description is three sentences: a headline, an elaboration, and a parameter explanation. It is front-loaded with the core purpose and concise with no redundant 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?

Given the presence of an output schema, the description does not need to detail return values. It adequately explains the tool's scope (unified dashboard across providers, savings) and the period parameter. Minor gap: could mention that it aggregates data, but the output schema likely covers structure.

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 schema has 0% description coverage, and the description compensates by explicitly listing valid values for the 'period' parameter ('today', 'week', 'month', 'all') and explaining its purpose. This adds meaning beyond the schema's default and type.

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 clearly states it is a 'unified usage dashboard' covering 'Claude subscription, Codex, external APIs, and savings', which is a specific verb-resource combination. It distinguishes itself from siblings like llm_check_usage or llm_track_usage by emphasizing a comprehensive overview across multiple providers.

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?

The description implies usage for a comprehensive view via phrases like 'complete picture' and 'across all providers', but does not explicitly state when to use this tool versus alternatives like llm_check_usage or llm_track_usage. No exclusions or scenarios are mentioned.

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