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

With readOnlyHint already declaring a safe read, the description adds the underlying endpoint (GET /v1/apps/{app}/events), the pagination behavior, and the exact return shape. It doesn't mention rate limits, auth needs, or retention limits on older events, keeping it below the top band.

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 short sentences, front-loaded with what is listed and immediately followed by the endpoint and return shape. No filler or redundant restatement of the name.

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?

For a read-only paginated list with full schema coverage and no output schema, the description supplies the endpoint and response envelope, which is what an agent needs. It doesn't describe the shape of individual event entries, a minor remaining gap.

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%, so the schema already fully documents app, from, page, and per_page. The description adds no parameter-specific meaning beyond what the schema states, so the baseline 3 applies.

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?

States a specific verb (list) and resource (app activity events) and enumerates event kinds (deployments, scaling, restarts, collaborator changes), which separates it from raw-log and deployment-specific siblings. It doesn't name any sibling explicitly, so it falls just short of the top band.

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 plus the 'from last N hours' and pagination cues give clear context for when this is the right call (audit/activity history over a time window). No exclusions or named alternatives (e.g. get_app_logs) are provided, so it stops at clear-context level.

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