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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful behavior beyond that: it discloses the returned fields (cause, started_at, acknowledged_at, resolved_at) and the underlying endpoint, which matters since no output schema exists. It omits pagination defaults and rate-limit behavior.

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 tight sentences: identity/definition first, filter summary second, return shape and endpoint last. No filler or restated name/title, and nothing important is buried.

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 9-parameter read-only list tool with no output schema, the description covers what the resource is, how it can be filtered, and what fields come back. Minor gaps remain around pagination limits and total-result behavior, but the schema carries the parameter-level detail.

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 every parameter is already documented in structured data. The description only summarizes three of the nine filters and doesn't add syntax or semantics for team_name, heartbeat_id, page, or per_page, so it stays at the 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 gives a specific verb and resource ('List incidents') and helpfully defines the domain term as 'alerts triggered by monitors/heartbeats', which disambiguates it from status pages or on-call entries. It does not explicitly contrast with the sibling betterstack_get_incident, so the single-vs-collection distinction is left implicit.

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 names the available filter axes (date range, monitor, acknowledged/resolved state), which implies how the tool is used for narrowing results. However there is no explicit when-to-use guidance or exclusion pointing to get_incident for a single incident, or to acknowledge/resolve tools for state changes.

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