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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description usefully adds a real behavioral trait: output is bounded to 64 KB with truncated=true when cut. However, it is silent on the fact that advance_watermark moves a cursor (a state change inside a tool annotated read-only) and says nothing about ordering or the for_me_first default, which materially affect results.

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?

A single dense sentence, front-loaded with the core 'what happened since X' framing, and every clause adds content rather than restating the name. Slightly listy but no wasted phrasing.

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 an output schema exists, return shapes need not be explained, and the 64 KB/truncated note covers the main output caveat. Still, for a 5-parameter tool with zero schema descriptions, the semantics of advance_watermark and max_items are missing, keeping it below full 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?

Schema description coverage is 0% across 5 parameters, so the description must carry the load. It explains the 'since' cursor and the 'watermark:<name>' syntax, but leaves until, max_items (bounds 1-200), for_me_first, and advance_watermark entirely undocumented in both schema and prose.

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 names the resource (a digest of events since a cursor/watermark) and enumerates its contents: counts by type, namespace and actor, attention items, items addressed to you, and changed documents. That is far more specific than the title 'Get Digest'. It stops short of distinguishing itself from near-siblings such as poll_events, list_inbox, or get_audit_view.

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 implies the trigger condition ('since an event cursor or watermark:<name>'), which tells an agent how to start one, but gives no explicit when-to-use/when-not guidance and names no alternative tool. An agent must infer whether to use this instead of poll_events or list_inbox.

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