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

The description discloses that the project 'can take a few minutes to initialize' and tells the agent to check status with `get_project`, which is valuable behavioral context beyond the annotations. The annotations only state readOnlyHint=false, which implies mutation, so the description adds timing and fallback information. It doesn't mention cost implications or confirmation details, but the annotations already indicate non-read-only, so this is above baseline.

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?

The description is concise, with two short paragraphs that are front-loaded. The first sentence states the core purpose, the second provides critical user interaction guidance and status-check instructions, and the third efficiently adds bulk support information. Every sentence adds value, and there is no redundant detail.

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 the tool's complexity—6 parameters, no output schema, and mutation with long initialization—the description covers key operational aspects: asking the user for organization, initialization delay, and status-check fallback. It also notes bulk parameters. However, it doesn't explain what to do with the `confirm_cost_id` (e.g., need to get cost first), which is a gap given the sibling tool `supabase_get_cost` existschers. Still, it provides a solid foundation for an agent to proceed.

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 schema covers 0% of the parameters in descriptions, but the tool description mentions 'organization_ids' and 'confirm_cost_ids' in the bulk support note, adding meaning to those specific parameters. However, it does not explain 'confirm_cost_id' or 'region' values beyond the enum list, leaving the agent to infer their purpose. With 6 parameters and no schema-level descriptions, the tool description partially compensates but not fully, so a baseline of 3 is fair.

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 clearly states the tool's purpose: 'Creates a new Supabase project.' It identifies the verb (creates) and resource (Supabase project), and it distinguishes itself from siblings like 'supabase_pause_project' or 'supabase_restore_project' by the action. However, it doesn't explicitly contrast with `supabase_create_branch` or other creation tools, so sibling differentiation is not fully achieved.

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 description gives explicit usage instructions: 'Always ask the user which organization to create the project in,' which provides a required prerequisite for invocation. It also directs the user to use `get_project` to check status after creation, indicating a follow-up action. This clearly guides when to use the tool and what to do next, though it doesn't explicitly say when not to use it, but the alternatives are covered by the follow-up instruction.

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