Increments project version (patch, minor, or major) and updates CHANGELOG notes without committing changes.
Bump the version and add notes to CHANGELOG (no notes: Unreleased becomes the version). Does not commit.
| Name | Required | Description | Default |
|---|---|---|---|
| dir | Yes | ||
| level | No | patch | |
| notes | No | Markdown |
Changes observed during successful MCP inspections.
v0.4.0Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / properties / dir / descriptionRemoved value: -"Project folder (absolute path, or relative to the server's working directory)."Input schema / properties / notes / descriptionPrevious value: -"Markdown for the CHANGELOG entry, e.g. '### Fixed\\n\\n- Release workflow.'"New value: +"Markdown"v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With only destructiveHint=false in annotations, the description earns credit for disclosing two real behaviors: the fallback where the Unreleased heading becomes the version when no notes are supplied, and that the change is left uncommitted (dirty working tree). It still doesn't say which files are altered or whether the operation is reversible.
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?
Two sentences, zero waste, and the core action is front-loaded ahead of the edge case and the commit caveat.
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?
No output schema and a file-mutating tool with minimal annotations: the description should state which version file is targeted, whether it requires an existing CHANGELOG/git repo, and what is returned. Those gaps leave an agent guessing about prerequisites, though the core mechanics are covered.
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 coverage is 33%: only 'notes' is documented (as Markdown), and the description adds the meaningful default behavior when notes is empty. But 'dir' is completely undefined (project root? repo path?) and 'level' is left to the self-explanatory enum, so compensation for the low coverage is partial.
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?
Specific verb+resource: bumps the version and writes notes into the CHANGELOG, with a parenthetical on what happens when notes are empty. It implicitly separates itself from git_commit via 'Does not commit', though it never names the file(s) whose version is bumped.
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?
'Does not commit' hints that a follow-up commit (e.g. git_commit) is required, which is useful workflow context. But there is no explicit when-to-use statement, no precondition (clean tree, existing CHANGELOG), and no comparison to siblings like tag_and_release or publish_package.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.