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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: fixed name ordering, the absence of pagination or result limits, returned fields, and the exact status precedence chain including the 'pending (not yet set)' edge case, which prevents misreading the status ordering.

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?

Two compact sentences, front-loaded with scope and ordering before the status-precedence detail. Every clause carries information an agent needs: scope, sort order, returned data, status ranking, and the no-pagination constraint.

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?

With no output schema and no parameters, the description carries most of the burden and largely meets it by naming returned fields, the sort order, and the status precedence. It does not describe the shape of the configuration object or what an empty result looks like, 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?

The tool takes zero parameters and the schema is empty, so the baseline is 4. The description usefully clarifies that no filtering, pagination, or limit options exist, telling the agent it must filter client-side rather than look for parameter support.

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 and resource: 'List all non-deleted heartbeats in the authenticated organization', and adds ordering, returned fields (configuration, last-ping timestamps), and status semantics. It implicitly distinguishes itself from the singular heartbeat_get sibling, but never names it or other heartbeat siblings explicitly.

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?

Usage is implied by the scope statement (organization-wide, non-deleted only, no pagination), so an agent can infer this is the full-enumeration tool. It gives no explicit when-to-use versus heartbeat_get, heartbeat_incidents, or heartbeat_logs, and no exclusions.

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