Perform a three-way merge of base, ours, and theirs. Conflicts are marked with standard diff3 conflict markers.
| Name | Required | Description | Default |
|---|---|---|---|
| base | Yes | Common ancestor text | |
| ours | Yes | Our version of the text | |
| theirs | Yes | Their version of the text | |
| ours_label | No | Label for ours in conflict markers (default "ours") | |
| theirs_label | No | Label for theirs in conflict markers (default "theirs") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It provides one useful behavioral detail (conflicts marked with diff3 markers) but omits other important traits such as whether the operation is read-only, the exact return format, or how it handles edge cases like identical inputs. This is a partial disclosure.
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, front-loaded sentence that is direct and free of redundancy. Every word contributes to understanding the tool's purpose and key behavior, making it highly concise without losing substance.
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 tool is simple, and the schema fully documents all parameters. However, with no output schema, the description should explicitly indicate what the tool returns (e.g., merged text), which it does not do. The mention of conflict markers implicitly suggests the output, but the lack of explicit return information leaves a completeness 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 100%, so the baseline is 3. The description names the required parameters (base, ours, theirs) and mentions labels only indirectly via conflict markers, but it does not add meaning beyond the schema's parameter descriptions. No extra semantic value is provided.
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 clearly states the tool's function as a three-way merge with specific resources (base, ours, theirs) and includes a behavioral detail about conflict markers. It distinguishes itself from sibling tools like text_diff and apply_patch by focusing on merging rather than diffing or patching.
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 implies the usage context (when you have a base and two modified versions) but does not explicitly state when to use this tool versus alternatives like text_diff or apply_patch. No exclusions or alternative recommendations are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: applying patches, validating patches, generating diffs for text and JSON, computing stats, and merging with conflict markers. No two tools could be confused with each other based on their descriptions.
Most tool names follow a similar object_verb pattern (json_diff, text_diff, patch_validate, three_way_merge), but apply_patch breaks this with verb_object order, and diff_stats is an odd noun-noun combination. Overall still readable and largely consistent.
Six tools is an ideal size for a focused diff/patch toolkit. Each tool serves a distinct function without redundancy or unnecessary bloat.
The toolkit covers the full lifecycle of diffing, patching, validating, analyzing, and merging, with specific support for both text and JSON. No obvious gaps in the stated domain.