optimize_efficiency

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

Annotations declare readOnlyHint and idempotentHint, indicating safe read operations. The description adds behavioral details: it either fetches from board (codename) or computes locally (text), and returns metrics, suggestions, and references. No contradiction with annotations.

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 moderately sized (4 sentences) and well-structured: it starts with the core purpose, then explains input options, then lists outputs, and finally gives usage examples. Every sentence adds value; no fluff.

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 tool has two optional parameters (one of each required), an output schema (present), and annotations, the description covers inputs, outputs, and use cases. It mentions what is returned (metrics, suggestions, references). Minor gap: behavior when both parameters are provided is not specified, but overall it is sufficiently complete.

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 100% (both parameters have descriptions). The tool description adds meaning beyond the schema: it clarifies that codename fetches from the leaderboard while text computes locally, and gives examples of acceptable text formats (ccusage JSON or specific strings). This enriches the semantic understanding.

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 returns actionable suggestions for improving token cascade efficiency, tied to current metrics. It explicitly differentiates from siblings by naming specific queries and mentioning the two input modes (codename or raw token pillars). The verb 'returns' and resource 'suggestions for efficiency' are specific and unique.

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 includes explicit use-case examples like 'when users ask 'how can I use AI more efficiently?'' and explains the two input options (codename vs. text). It also notes that at least one is required. While it doesn't list when not to use it, the sibling tool names imply alternatives for comparison or description tasks.

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