skypilot_tail_provision_logs

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

readOnlyHint=true already tells the agent this is a safe read. The description usefully adds the default tail (100) and the 'set to 0 for all' semantics, which is genuinely actionable behavior. But it says nothing about failure modes (e.g., cluster not provisioned, missing log file) or multi-worker default behavior, so the added value is moderate.

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 crisp sentences, front-loaded with what the tool returns, then worker indexing, then the tail semantics. No filler or repetition.

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?

Output schema exists, so return-value format need not be explained. For a read-only, 3-param log retrieval tool, the description covers purpose, both optional params' semantics, and defaults. It only lacks edge-case mention (e.g., what happens if no provision.log exists), a minor gap.

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 0%, so the description must compensate. It does: explains worker is an optional node index for multi-node clusters, and tail defaults to 100 with 0 meaning all lines. cluster_name meaning is obvious. It doesn't clarify tail negative-value behavior or worker indexing base, but it substantially lifts the undocumented schema.

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 (get/tail) and resource (provisioning logs / provision.log) for a cluster, and clarifies this is provisioning-time output. Easily distinguished from siblings like skypilot_tail_autostop_logs, skypilot_pool_logs, and skypilot_api_server_logs by the 'provision.log' qualifier.

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?

Implied usage: retrieve provisioning logs for a cluster, with optional worker index and tail count. But it doesn't state when to use this vs other log tools (autostop logs, api server logs), nor when not to use it, leaving the agent to infer from the log-type distinction alone.

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