Run SSH Task

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false. The description enhances this by clarifying the execution policy behavior: blocked on production/read-only and requiring content-bound confirmation on guarded systems because tasks may execute commands or transfer files, adding genuine value about side effects without contradicting annotations.

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 sentences with essential information about execution policy and safety delivered efficiently. Each sentence serves a purpose, though the 'selected saved connection' phrasing is slightly verbose.

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 task-runner with nested objects and an output schema, the description gives appropriate context about side effects and policy restrictions. The existence of an output schema reduces the need to document return values, and the description covers the ambiguity of what 'saved task' means in terms of policy constraints effectively.

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 the description focuses on the tool's behavior rather than explaining individual parameters. The description clarifies the 'inputs' concept generally by noting tasks may execute commands or transfer files, but with 8 parameters and no explanation of confirm vs confirmationText vs confirmation_text (a likely inconsistency worth mentioning) or secretInputNames, the description could have compensated more for the lack of schema coverage.

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?

The description clearly states the tool starts a saved SSH task on its selected saved connection, using the specific verb 'starts' with the resource being the saved SSH task/connection. It partially distinguishes from siblings by explaining the policy implications (production/read-only blocks execution, guarded needs confirmation), which relates to when operations proceed.

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?

While it doesn't name alternatives explicitly, the policy language tells the agent when execution will be blocked or need confirmation, which is crucial for an agent deciding to call this. It provides useful context about the execution context even though it could be more explicit about when to use this versus other SSH sibling tools.

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