run_post_install_task

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the agent knows this is a non-destructive but state-changing external call. The description adds that execution is a Jenkins/Ansible task run, but says nothing about whether it is asynchronous, how long it takes, how to poll status, or what permissions are required. With annotations carrying the safety profile, this is a limited but non-zero contribution.

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 verb and resource, then appends the task-source pointer and an example. Every clause earns its place, though the parenthetical '(jenkins/call)' is backend detail an agent does not need for tool selection.

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 mutating, externally-executed task runner with no output schema, the description omits important context: whether the call returns immediately or produces a job to poll (check_task exists as a sibling), whether required confirm gating is enforced, and what the arbitrary params object should contain. Annotations cover the safety profile but not the execution lifecycle.

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 description coverage is 100%, so id, task, params and confirm are all documented in the schema itself, including the constraint that confirm must be true. The description's statements about 'task ID or name from list_post_install_tasks' and 'extra params' merely restate schema content, adding no format, default, or constraint detail beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 a Jenkins/Ansible task on a server') and even names the backing endpoint (jenkins/call), so the action is unambiguous. It points to list_post_install_tasks as the source of task identifiers and gives a concrete scenario (GPU drivers after OS reinstall). It stops short of contrasting itself against the closest siblings such as create_reinstall_task or check_task, which would earn 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?

The example ('installing GPU drivers after OS reinstall') implies the post-install context, and the pointer to list_post_install_tasks tells the agent where to obtain the task argument. However, there is no explicit when-not-to-use guidance, no mention of alternative task tools (create_reinstall_task, check_task), and no note on prerequisites such as the server being in a post-reinstall state.

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