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

The description goes well beyond the annotations: it discloses the auto-created default calendar (Mon-Fri, 8:00-13:00 and 14:00-17:00), the account owner becoming project owner, an explicit permission requirement ('Requires write permission'), and a concrete consequence of non-idempotency ('Calling it twice creates two projects'), which makes idempotentHint=false tangible. It does not cover what happens if the derived/key collides with an existing project, so not a 5.

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, each carrying distinct information: what gets created, what is returned, and the duplicate-call and permission caveats. Front-loaded with the action and fully free of padding.

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?

Given seven optional-heavy parameters, no output schema, and the description carrying the return value ('projectId'), it is nearly complete: defaults, permissions, side effects, and non-idempotency are all present. The remaining gap is error behavior — e.g. duplicate project key or invalid workspace — which an agent would benefit from knowing before calling.

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 all seven parameters (including key derivation, currency default EUR, startDate default today, and the non-moving deadline semantics) are already fully documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 empty project in the connected account') and enumerates the side effects (default calendar, owner assignment). The word 'empty' implicitly distinguishes it from create_project_from_plan and create_project_from_template, though those siblings are never named, so the differentiation is inferential rather than explicit.

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?

The note 'Returns the projectId for adding tasks' implies this is the first step in a task-building workflow, which is useful implied usage guidance. However, there is no explicit when-to-use versus when-to-use-an-alternative statement — the agent must infer that template/plan-based creation exists for non-empty projects.

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