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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false. The description goes beyond them by disclosing the return payload and, crucially, guarding against the non-idempotent duplicate-creation trap via the 'prefer existing' workflow. It stops short of stating what happens on name collisions or permission requirements, so it is strong but not exhaustive.

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 sentences, each earning its place: the action and return value first, then the routing/preference rule, then the escalation rule. Front-loaded with zero redundancy.

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 one-parameter creation tool with no output schema, the description covers action, scope, return fields, and the decision workflow. Nothing an agent needs to invoke it correctly is missing.

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?

The single 'name' parameter is documented at 100% schema coverage ('The name of the new project'). The description adds no syntax, length, or uniqueness constraints beyond the schema, so the baseline 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+resource ('Create a project'), names the scope ('for the connected team'), and even declares the return fields (id, name, dashboard link). It is trivially distinguishable from siblings like list_projects or create_dataset.

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?

Explicit when-to-use: 'Prefer an existing project: call list_projects first, and create a new one only if the team has none or the user explicitly asked for one.' It names the alternative tool and the exact conditions, plus a fallback instruction to ask the user when unsure.

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