Create Table

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

Adds substantial context beyond the annotations: the storage inheritance order, the fact that the API does not return S3 credentials in cluster metadata, the required organization-admin authorization, and a reconciliation path via list-tables before retrying. These are non-obvious traits annotations cannot express.

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?

Bold section headers front-load purpose and behavior, and each section earns its place. The Credentials and Auth blocks are slightly verbose relative to the single required parameter, so it falls short of a 5.

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 mutation tool with a nested S3 object and no output schema, the description covers return contents, auth, credential caveats, inheritance behavior, and failure recovery. Nothing an agent needs to call 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?

With 100% schema coverage the baseline is 3, but the description adds real meaning: the omission-inheritance semantics of s3Storage, that paths default to the bucket root, and that externalId must exactly match the value configured in AWS. This goes past what the schema documents.

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 an empty RawTree table in a database') plus the optional S3 storage variant, which cleanly separates it from create-database and create-cluster siblings. An agent can tell what it produces (an empty table) without opening the schema.

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 clear conditional guidance: omit s3Storage to inherit database then cluster default storage, or supply a complete s3Storage object for an explicit override, and names list-tables as the tool to reconcile an ambiguous response. It lacks an explicit statement of when NOT to use it versus create-database/create-cluster, keeping it below a 5.

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