Save project as

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

Annotations already declare destructiveHint=true and idempotentHint=true. The description adds genuinely new context: the open project pointer moves to the new file, extension is inferred from the path and auto-appended, and overwrite defaults to failing when the file exists. It does not mention authorization or teamwork/check-in implications, which is the remaining gap for a mutation-heavy tool.

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?

Front-loads the core action and the caller-visible side effect, then packs formats, defaults, exclusion guidance and return shape into a compact block. Slightly dense as one paragraph, and the trailing return-shape clause is the least polished, but virtually every sentence carries 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?

No output schema exists, yet the description still states the return shape {saved, format, file, project}. Combined with format rules, overwrite/folder defaults inherited from the schema, and the export-tool exclusion, 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 description coverage is 100%, so baseline is 3, but the description earns above baseline by decoding the format enum (pln=solo, pla=archive incl. library parts, tpl=template, pln25/pla25=Archicad 25 previous version) and clarifying that format defaults from the path extension. This adds meaning the enum names alone do not convey.

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+resource ('Saves the project under a new file') and immediately scopes it with the File > Save As analogy. The list of supported formats and the explicit pointer to export tools for other output types makes it unambiguously distinguishable from save_project, open_project, and the export_* siblings.

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?

Explicitly routes non-native output away: 'For IFC/DWG/PDF/image exports use the export tools instead.' The behavioral note that the open project afterwards refers to the new file implicitly tells the agent when this differs from a plain save. It stops short of naming save_project directly as the alternative for in-place saves.

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