Create collection

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the non-idempotent nature of the create by warning against blind retries and prescribing a read-back-and-reconcile procedure after 429, LIMIT_EXCEEDED, timeouts, or other uncertain results. It does not discuss permissions, the shape of the response, or what side effects a DYNAMIC collection's filter has.

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 front-loaded with a distinct purpose: what it creates, which fields are required and how types differ, and how to safely handle uncertain results. There is no filler and the riskiest guidance is stated directly.

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 nested-object create tool with no annotations and no output schema, the description covers the required fields, enum values, the DYNAMIC conditional, schema lookup, and retry safety. It leaves out the response shape and any permission or rate-limit context beyond the 429 mention, but those are secondary for this tool.

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 coverage is 100%, so a baseline of 3 is expected, but the description adds real value beyond the schema: it supplies the enum values (ACTIVE|INACTIVE, STATIC|DYNAMIC) and the conditional dependency that DYNAMIC requires a dynamic_filter, none of which appear in the schema's enum metadata. It also points to get_operation_schema for the nested request shape.

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 opens with a specific verb and resource ('Create a new collection') and lists the required fields, so the agent knows exactly what operation this is. It does not explicitly name sibling tools like update_collection, but the word 'new' plus the create semantics sufficiently separates it from the CRUD siblings.

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?

It gives concrete usage context: which fields are required, how STATIC vs DYNAMIC differ, and directs the agent to get_operation_schema("CreateCollection") for the exact request shape. It also supplies explicit retry guidance for 429/LIMIT_EXCEEDED/timeout, which is the highest-risk part of calling a create tool. It stops short of stating when to prefer update_collection or other alternatives.

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