pool_push_image

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

Beyond the annotations (destructiveHint=true, readOnly=false), the description adds crucial details: the irreversible recreation of every desktop, the preview step that reports affected-desktop and in-session-user counts, the confirm=True scheduling behavior, and the audited nature. This fully discloses the destructive implications and procedural safeguards.

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?

The description is compact yet dense, leading with the most critical warning and then providing an organized Args list. Every sentence contributes value—no filler or redundant repetition. The structure front-loads the blast radius, then explains the action and parameters.

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 destructive, multi-parameter tool with no output schema, the description covers all essentials: purpose, effect, preview/confirm flow, parameter semantics, and provenance of inputs. It even anticipates the user's need to see blast radius before committing. The tool is fully comprehensible without needing to guess at behavior.

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 descriptions are absent (0% coverage), but the 'Args' section compensates thoroughly by explaining each parameter's role, defaults, and valid values. For example, logoff_policy is specified as 'WAIT_FOR_LOGOFF (default) or FORCE_LOGOFF,' and confirm is clarified as a preview/schedule switch.

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's function: 'Apply the pending image to an instant-clone pool' with the dramatic outcome 'RECREATES EVERY DESKTOP in it.' This specific verb-object pairing and scope make its purpose unmistakable, distinguishing it from siblings like pool_get or pool_set_enabled.

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?

The description provides strong usage context by labeling it the 'Highest blast radius in the family' and instructing to preview with confirm=False before scheduling. It does not explicitly name alternatives or say when not to use, but the unique nature of the tool and clear workflow guidance suffice for a high score.

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