resume

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

With no annotations, the description carries the full burden and does disclose non-obvious behavior: the continuation runs in its own agent session and branch and is materialized as a NEW run id rather than mutating the original. It does not cover failure modes (what happens on a running or cancelled run), permission requirements, or whether state is consumed, so the mutation/resume safety story is incomplete.

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 sentences, front-loaded with the core action and effect, then the three state-dependent input meanings in a compact clause list. No filler or restated name/title.

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 two-parameter tool with no output schema and no annotations, the description covers purpose, effect scope, and input semantics well; the implied return (a new run id) is stated. It falls short of complete because error/edge-case behavior is unaddressed for a tool whose whole meaning depends on the run's current state.

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 coverage is 0% and neither parameter is typed beyond 'string', so the description has to supply meaning; it does so for `input` by defining it differently per run state (answer, follow-up instruction, reply). `run_id` is only implicitly defined as the run being continued, which is adequate but not explicit.

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 ("Continue a run") plus the scope of the effect: it happens in the run's own agent session and branch and yields a new run id. An agent can tell this apart from a fresh `run` or a `chain` invocation only by inference, since no sibling is named, which keeps it short of a 5.

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?

Gives explicit state-based selection guidance: on a waiting run it supplies the answer to the pending question, on a finished run a follow-up instruction, on a paused chain a developer reply. That covers the main 'when to use' cases clearly, but it gives no exclusions, e.g. what to do with a currently running run or when to prefer `run` or `execute` instead.

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