st.config.patch

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

With no annotations, the description carries the behavioral burden and does disclose important side effects: the operation mutates config.yaml, requires explicit confirmation and a prior snapshot, and usually requires a restart. The 'usually' phrasing is somewhat vague, but this is substantially more transparent than typical tool descriptions.

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 one compact sentence with no fluff. It front-loads what the tool does, then states the critical prerequisites and post-condition.

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?

This is a mutation tool with no annotations and no output schema, so the description should explain parameters, return behavior, and safety details more fully. Five parameters are undocumented, and no information is given about what success or failure looks like, making the description insufficient for safe invocation.

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%, and the description must compensate. It explains the dotted-path mechanism and confirms the need for confirm:true, but it does not explain key parameters like updates, unset, allowUnknown, or snapshotLabel, leaving the agent to guess their structure and meaning.

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 names the exact resource (config.yaml), the action (Patch), and the method (by dotted paths). This clearly distinguishes it from sibling tools like st.resource.patch and st.config.get.

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 clear preconditions: confirm must be true, snapshots must be taken first, and a restart may be needed. It does not explicitly name alternatives or exclusions, but the context for usage is clear enough.

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