action_run

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

With no annotations, the description carries the full behavioral burden and does disclose one genuinely non-obvious trait: MCP request cancellation does not cancel the action, implying fire-and-check semantics. However, it says nothing about permissions/auth, side effects or destructiveness, whether the call blocks, or the confirmation_token flow for risky actions (only the schema hints at that).

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 short sentences, zero filler, with the core purpose and the parameterization/schema rule front-loaded and the cancellation caveat last. Every sentence earns its place.

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 tool with an output schema and four parameters, the essentials are covered: what runs, how to supply params, where to find the schema, and the cancellation caveat. The gap is the plan/confirmation-token workflow for guarded actions, which the description leaves to the schema.

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 75% (params, runtime, confirmation_token all documented in-schema; only 'action' is bare). The description adds only that params holds 'typed' values for a parameterized action and that action_info yields the advisory schema. Baseline 3 is appropriate when the schema already documents most 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+resource ('Run one non-interactive action') and scopes it to non-interactive execution, which separates it from interactive variants. It also cross-references action_info for schema discovery, implicitly distinguishing itself from that lookup tool. It stops short of naming action_result/action_cancel, but the core purpose is unambiguous.

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 clear context: use this to run a single non-interactive action, pass params only for parameterized actions, and consult action_info for the advisory schema. The 'non-interactive' qualifier implicitly excludes interactive actions. No explicit when-not guidance relative to plan/up/down or how to retrieve results via action_result.

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