skypilot_serve_logs

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

readOnlyHint already declares the safe-read profile, and the description adds real context beyond it: 'snapshot' semantics, 'Does not stream/follow', and tail=0 meaning all lines. That clarifies non-streaming behavior an agent needs. It stops short of noting anything about permissions or rate limits, but for a read-only log fetch that is minor.

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?

Four short sentences, zero filler, front-loaded with the purpose before constraints. Every sentence adds actionable information.

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?

An output schema exists, so return-shape detail is not required, and the parameter behavior around target/replica_id/tail is well covered. The only gap is not routing the agent away from the similarly-named download-logs sibling.

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, and it largely does: it enumerates target values ('controller', 'load_balancer', 'replica'), explains tail (default 100, 0 = all) and the replica_id conditionality. Only service_name goes unmentioned, though its meaning is self-evident.

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?

Clear specific verb+resource: 'Get a snapshot of logs from a service component.' It scopes to a specific component (with 'controller'/'load_balancer'/'replica' targets), which distinguishes it from generic job/pool log tools. However, it does not explicitly differentiate itself from the close sibling skypilot_serve_download_logs, which a reader might confuse with it.

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?

It gives conditional guidance for one parameter ('When target is replica, optionally specify replica_id'), which is genuinely useful. But it never states when to use this tool versus siblings like skypilot_serve_download_logs or skypilot_api_server_logs, so selection context is only implied.

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