New project

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety bar is partly met. The description adds real value beyond that: it discloses that the current project is closed, that unsaved changes must be resolved (saveFirst vs discardChanges), and even the return shape. It does not restate the untitled-project saveFirst failure, which lives only in the schema.

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 destructive action, then packs templates, reset, the unsaved-changes requirement, and the return shape into a compact passage. Parentheticals are dense but each carries information; slightly heavy but no filler sentences.

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 4-param destructive tool with no output schema, the description covers the side effects, the mutually exclusive save options, and the return value ({created, project}). Nothing essential for a correct call is missing, though edge cases like untitled-project saveFirst failure are left to the schema.

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 100%, so the baseline is 3. The description still adds meaning: it pairs reset with the 'New & Reset' concept, points template at installed .tpl files discoverable via get_project_info, and frames saveFirst/discardChanges as a required either/or decision.

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 ('Creates a new untitled project') and immediately scopes the side effect ('CLOSING the current one'). This clearly separates it from siblings like open_project, close_project, and save_project_as.

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 concrete conditions: use a .tpl template, or reset:true for New & Reset, and explicitly routes the agent to get_project_info {includeTemplates: true} to list templates. It also states the unsaved-changes decision that must be made. It does not explicitly contrast with open_project/close_project, so a 4 rather than 5.

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