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

The description extensively explains behavioral traits beyond annotations: it moves the tracker, pauses measurement, stops spending, keeps sheet and scores readable, and is idempotent for already archived trackers. Annotations hint at destructive and idempotent, but the description adds concrete context.

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 action and then elaborates efficiently. Every sentence earns its place, though it could be slightly streamlined without losing 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 2 parameters and no output schema, the description covers most aspects: purpose, effects, idempotency, and persistence. It lacks mention of potential errors or return values, but these are not critical for a state-changing tool with annotations.

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?

With 100% schema coverage, the schema already documents both parameters. The description reiterates the parameter meanings but does not add new information beyond what the schema provides, so it scores at baseline.

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 that the tool archives a finished tracker, detailing the specific effects like moving to the end of the list, pausing measurement, and stopping spending. It distinguishes from siblings by focusing on trackers, and the title 'File a tracker away' aligns well.

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 gives explicit context for when to archive (finished campaign, sold brand, ended trial) and mentions reverting with archived false and start_tracker. However, it does not explicitly compare with sibling tools like archive_project or provide when-not-to-use guidance.

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