tokenpull

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

Annotations provide readOnlyHint=true, and the description adds that it reads from local session logs, does not read message content, and numbers remain local. It also discloses possible partial data (estimated=true) and dataGap notes, providing rich behavioral context beyond 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 front-loaded with the core purpose and is informative, but contains some redundancy (e.g., 'zero paste' mentioned twice) and could be slightly more concise. Overall, every sentence adds value.

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 single parameter, presence of output schema, and annotations, the description is complete. It covers purpose, data scope, privacy, and platform-specific nuances, leaving no obvious gaps for an AI agent to misuse the tool.

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 coverage is 100%, and the description adds significant meaning beyond enum values by explaining special platforms like 'multi', 'devin', 'codex', and 'other', along with setup requirements (e.g., copilot needs COPILOT_OTEL_ENABLED=true). This substantially aids parameter 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 the tool pulls local token usage and ranks it across four windows (7d/30d/90d/all-time) with a cascade. It distinguishes itself from siblings like tokenpull_submit and tokenpull_compare by emphasizing local retrieval and zero paste.

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 explains that the tool reads usage counts not message content, that data stays local unless submitted, and notes potential partial data with estimated=true. It provides context for when to use (pulling local token usage) but lacks explicit when-not-to-use statements or direct alternatives beyond implicit distinction from siblings.

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