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 real value beyond that by disclosing the returned field set and by tying the step id to next_step's expectsStep parameter — a cross-tool contract the agent could not infer from annotations or the empty schema.

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 compact sentence that front-loads the scope ('the runs going now') before the field list. The parenthetical about next_step's expectsStep is slightly dense but earns its place by encoding a real dependency.

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 zero-param read tool with no output schema, the description carries the return-shape burden and does so adequately by naming each field. It omits ordering, whether paused/blocked runs count as 'going', and any volume limits, which leaves modest gaps for a list operation.

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, so there is nothing to disambiguate and the baseline of 4 applies. The description correctly spends no space on inputs and instead describes outputs.

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+resource ('the runs going now') and enumerates the returned fields (id, name, routine, status, current step), so the agent knows exactly what it gets back. It implicitly separates itself from get_history (past runs) and get_run (a single run) via 'going now', though it never names 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?

Usage is only implied by the phrase 'going now' — the agent can infer this is for currently active runs rather than historical ones. There is no explicit when-to-use/when-not or named alternative such as get_history or get_run, and no mention of whether paused runs are included.

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