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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered. The description adds only a mild reinforcement of that read-only nature plus a hint that runs carry reserved credits and failure states; no pagination, freshness window, or scope constraints are disclosed.

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 tight sentences, front-loaded with the core action and closing with the exclusion. Zero filler.

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?

An output schema exists, so return values need no prose, and the read-only profile is annotation-covered. However, with 0% schema description coverage and a cursor-based list tool, the absence of pagination and filtering guidance leaves the definition short of complete.

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%, so the description must carry the load, yet it never explains limit, cursor (pagination), or the automationId filter. "Recent" vaguely gestures at the default window but gives no actual semantics for any of the four parameters.

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 (Read) and resource (automation runs) with the extra fields it surfaces (status, reserved credits, failures). The plural scope cleanly separates it from get_automation_run and list_automations, though it doesn't name those 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?

"Does not start or retry work" is a genuine when-not boundary that rules out the activate/resume/retry family, but no positive trigger or named alternative is given (e.g., when to prefer this over get_automation_run or list_automations). Usage is implied rather than stated.

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