ae_newProject

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds the materially important behavior that the call can be refused and that discardChanges overrides the refusal, which is exactly the kind of context annotations don't carry. Note the slight tension: discardChanges:true implicitly destroys unsaved work while destructiveHint is false, but the description warns about this rather than contradicting it. It does not say what happens to the prior project or what state is returned.

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?

One sentence, front-loaded with the action, with the refusal condition and escape hatch in a tight parenthetical. Every clause carries information; nothing is redundant or padded.

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 single-parameter, non-open-world tool with no output schema, the description covers purpose, precondition, and the one parameter's escape-hatch behavior. What is missing is post-call state (is the previous project closed? what does a new project look like?), which matters for a mutation tool with no return-value documentation.

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 carries the burden for the single parameter, and it does: it defines discardChanges as the override that allows discarding an unsaved project. That is the meaningful semantics an agent needs. It omits the default value and any indication of the boolean's false case beyond the refusal sentence.

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 gives a specific verb and resource ('start a new empty project') scoped to After Effects, so it is clearly distinguishable from ae_openProject or pr_newProject by the 'empty/new' framing. It stops short of explicitly naming the alternative it is not (opening an existing project), so it falls just short of a 5.

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 states a clear precondition: the call refuses if the current project is unsaved unless discardChanges is set. That is real when-to-use guidance. However, it never contrasts this with ae_openProject or explains what an agent should do instead when the refusal fires, so an explicit alternative path is missing.

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