Limit eaten by chat

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

With no annotations, the description carries the full burden, and it does disclose the key behavioral quirk (shared account-wide gauge, no local trace for chat/mobile) and the validation strategy. However, it does not state whether the tool is read-only, what it returns at the top level, or whether it mutates anything—a notable gap for an unannotated tool.

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 prose is dense and includes useful context, but it could be tightened; phrases like 'subtracts what local logs explain from what the gauge actually did' are more convoluted than necessary. The view enumeration is concise and helps navigation, yet the overall structure is not ideally front-loaded.

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?

The description provides enough to select a view and understand the underlying method, but no output schema exists and the description never describes the result structure. Given the tool's non-obvious semantics, an example of the returned comparison would materially improve completeness.

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 covers 100% of the single parameter, but the description goes beyond 'which angle' by explaining what each enum value reports: weekly summary vs. ground truth, per-5-hour windows, and source coverage. This makes the enum actionable for an agent.

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 explains a calculation—subtract local-log-explained usage from the total gauge and validate against the product breakdown—but never states the tool's core purpose as a direct verb+object. The title 'Limit eaten by chat' and the name only imply that it measures chat's share. It also does not clearly distinguish itself from the sibling limit_breakdown tool.

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 or when-not-to-use statement, and no sibling tool is named. The clause 'log-only tools undercount' hints at a scenario where this tool adds value, but an agent is left to infer the conditions for choosing chat_share over current_limits or limit_breakdown.

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