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

Beyond the readOnlyHint and idempotentHint annotations, the description explains key behaviors: returns deletes, uses a global seq counter where gaps are other accounts' events, and instructs to judge completeness from has_more not seq. This adds essential interpretation 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?

Three sentences deliver purpose, return shape, usage, and critical caveats without wasted words. The information is front-loaded and every sentence earns its place.

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's cursor-based pagination and the lack of an output schema, the description fully covers return values, pagination flow, and how to interpret gaps and completeness. It leaves no major usage questions unanswered.

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 description adds significant meaning to the `since` parameter, explaining exactly how to use it as a cursor. With schema coverage at 67%, the description compensates for the unexplained `limit` parameter by emphasizing the cursor mechanism and has_more, though it doesn't detail entities or limit behavior.

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's function: it reports changes since a cursor, explicitly including deletes, which distinguishes it from list reads. The specific verb 'changed' and resource 'events' make the purpose unmistakable.

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?

It provides explicit usage instructions: pass the last seq as `since` for subsequent calls, omit for first sync. It also explains when to prefer this over a list read (to see deletes), though it doesn't name a specific sibling alternative.

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