Code MCP Server

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool previews changes, implying a read-only operation, but doesn't disclose any behavioral traits such as what changes are previewed (e.g., staged vs. unstaged in Git), how the preview is presented, or any limitations (e.g., performance, scope). This is a significant gap for a tool with no annotation coverage.

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 a single, efficient sentence: 'Preview all changes before committing'. It's front-loaded with the core action and purpose, with zero wasted words. Every part of the sentence contributes to understanding the tool's intent.

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?

Given the complexity implied by the tool's name and sibling tools (e.g., 'preview_changes_enhanced'), the description is incomplete. No annotations or output schema exist to clarify behavior or results, and the description lacks details on what changes are previewed, how they're displayed, or any constraints. This is inadequate for a tool in a context-rich environment like code or file management.

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 tool has 0 parameters, and the input schema has 100% description coverage (though empty). The description doesn't need to add parameter semantics, as there are none to explain. This meets the baseline for a parameterless tool, but doesn't provide extra value beyond the 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?

The description 'Preview all changes before committing' states the tool's purpose with a verb ('preview') and resource ('changes'), but it's vague about what changes are being previewed (e.g., code, files, configurations). It distinguishes from some siblings like 'apply_patch' or 'auto_commit_changes' by focusing on previewing rather than applying, but the scope remains unclear compared to 'preview_changes_enhanced'.

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 provides no explicit guidance on when to use this tool versus alternatives. It implies usage before committing changes, but doesn't specify prerequisites, conditions, or when to choose it over siblings like 'preview_changes_enhanced' or 'git_diff'. There's no mention of exclusions or alternatives, leaving the agent to infer context.

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