Project

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

Annotations already flag destructiveHint=true, readOnlyHint=false and non-idempotency, so the safety bar is lower; the description still adds genuinely new behavior. It discloses that save to an existing destination is refused to avoid a blocking modal, which is an error path an agent would otherwise hit blind, and warns of track-loss risk before opening. It does not state what happens to the currently loaded project when open succeeds.

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?

Three compact sentences with the operation stated first, then the save restriction, then the precondition/alternative. Every clause carries information; the only mild cost is that the audacity_fresh sentence is dense and requires knowing that sibling's signature.

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?

For a two-parameter mutation tool with no output schema and annotations already covering the safety profile, the description covers operation, precondition, refusal behavior and the safer alternative. A return-value or failure-shape note would close the last 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 coverage is 0%, so the description must carry the parameter burden, and it does substantially: 'file' is defined as an .aup3 path whose meaning switches by action, and 'action' semantics are spelled out for both the open and save cases, including the save-only restriction on new paths. Remaining gaps are edge cases such as a nonexistent file on open or non-.aup3 input.

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 names two concrete operations on a concrete resource: opening an existing .aup3 into an empty project, or saving to a new .aup3 path. That is specific enough for an agent to tell it apart from audacity_fresh, which it names explicitly. It stops short of 5 only because the relationship to siblings such as audacity_project_info or audacity_launch is not addressed.

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?

It gives a real routing rule: use audacity_fresh with backupTo before opening when tracks are present, plus the constraint that existing save destinations are refused. It also states the precondition that the target project must be empty. There is no explicit guidance on when to prefer project_info or launch instead, so it is clear but not exhaustive.

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