save_version

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

With no annotations, the description carries the full burden and does so: it names the side effect (writes to a git repo in the user's project folder), the exact file scope saved and excluded, the required user confirmation, what the result reports back ('what was saved and the changed Dims values'), and the shared HTTP/SSH server behavior where nothing runs and commands are returned instead.

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?

Dense and front-loaded — file scope, then trigger conditions, then parameters, then the server fallback — with essentially no filler. The semicolon-chained fragments make it slightly harder to scan than it could be, keeping it just short of top marks.

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?

Output schema exists, and the description still usefully says the result reports what was saved plus changed Dims values. Combined with the file-scope list, confirmation gating and the remote-server fallback, an agent has everything needed to invoke this correctly.

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 0%, so the description must explain all three parameters and does: message is 'what changed, in the user's words' with a concrete example format, part is 'only that part (default: all)', and start performs one-time repo initialization with a .gitignore under a stated condition. Each parameter gets meaning beyond its type and default.

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?

States a specific verb and resource ('Save a version of the project in its version history') and enumerates exactly what is captured: each part's script, ref/ folder, MEASURE.md, adjacent .py files and b123d-print.toml, explicitly excluding out/. It is clearly separable from siblings list_versions and restore_version.

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?

Gives an explicit preconditions and exclusion rule: only after the user says yes, only after a change that built and passed its checks, and it tells the agent to OFFER 'Save this version? ...' rather than calling on its own. It also gates start=True on the user having agreed to a version history, so both when-to-use and when-not are covered.

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