Supabase: Create bucket

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is known; the description adds only that a bucket may be public (no auth) or private. It omits behavior an agent needs for a destructive, non-idempotent mutation: whether creation collides with an existing bucket, required permission level, and whether deletion of data is possible. The public-access implication is useful but thin.

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?

Two short sentences, front-loaded with the operation, with no filler beyond the opaque '[UNIFIED]' tag. It is efficient, but the brevity comes at the cost of the details noted elsewhere rather than being genuinely complete.

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 destructive, non-idempotent creation tool with five undocumented parameters and no output schema, the description is far too sparse. An agent cannot tell what 'site' expects, how to express file size limits or MIME type lists, or what the collision/failure behavior is when the bucket already exists.

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 0% across 5 parameters, so the description carries the full burden and largely fails it. It clarifies only the 'public' flag's meaning (accessible without auth) and says nothing about 'site', 'name', 'file_size_limit' (format of the size string), or 'allowed_mime_types' (expected string encoding for a list of MIME types).

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 ('Create a new storage bucket') that an agent can immediately map to the sibling family (supabase_delete_bucket, supabase_update_bucket, supabase_get_bucket). It does not explicitly name those alternatives, but the create semantics are unambiguous. The '[UNIFIED]' prefix is unexplained noise rather than added clarity.

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?

There is no guidance on when to create a bucket versus reusing an existing one, no prerequisites (project/site context, permissions), and no mention of what happens if the bucket name already exists. The only usage-adjacent content is the public/private choice, which is described in the parameter sense rather than as a decision guideline.

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