context_apply

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

The description discloses a key behavioral trait: if any baseline changes, the entire group commit is rejected, which warns the agent about a potential failure mode. However, it does not specify side effects, whether the operation is destructive, or what a successful commit entails. With annotations limited to openWorldHint=false, the description carries the burden but only partially.

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?

One concise sentence that front-loads the action and then adds the critical rejection condition. No filler words; every clause adds 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?

The description explains the input source and a key failure condition, and an output schema exists to cover return values. But for a mutating apply-style tool with minimal annotations, it lacks detail on what changes are actually made, whether they are reversible, and what the agent should do if the commit is rejected (e.g., re-run preview). This leaves the tool usable but not fully self-contained.

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?

The single 'plan' parameter has no description in the schema and additionalProperties is true, so the schema conveys almost nothing about its structure. The description compensates by telling the agent exactly where the plan comes from: the return value of context_preview or context_preview_remove. This gives meaning to the parameter that the schema lacks.

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 states a specific action ('保存' = save/commit) on a specific resource (the plan returned by context_preview or context_preview_remove), and the rejection condition further clarifies its role. It is clear enough to distinguish from sibling apply tools like module_apply or host_apply, though '保存' is slightly ambiguous versus the tool name 'apply'.

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 explicitly names context_preview and context_preview_remove as the sources of the plan, telling an agent this tool should be invoked after those preview tools produce a plan. It does not explicitly list exclusions or alternatives, but the workflow is clear from the source references.

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