create_snapshot

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

With all annotation hints set to false, the description carries the burden of explaining behavior. It adds meaningful context by disclosing that this call returns immediately and that persistence must be confirmed via snapshot_status. It also mentions the confirm=true prerequisite, which is the useful and not captured by the annotations. It could go further on effects of wait_for_completion or include_global_state, but the core behavioral disclosure is strong.

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 two sentences with no filler and the purpose is front-loaded. It packs the final semantics into a concise sentence and keeps the key identifying purpose first. Every sentence earns its place.

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?

The description covers the essential flow: create, non-blocking, poll, and prerequisite. It omits the semantics of wait_for_completion=true and include_global_state, which are likely to matter for an agent deciding how to invoke the tool correctly. The schema makes up some parameter defaults, but given only two required parameters and several optionals, the description is at minimum viable completeness.

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%, so the description must compensate for the six parameters. It only indirectly covers: repository, indices, and confirm. The important parameters wait_for_completion and include_global_state are not explained in the description. The phrase 'non-blocking by default' implies wait_for_completion, but it is not stated directly. This materially falls short of the required parameter guidance.

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 'Create a snapshot of selected indices into a repository,' which states a specific verb and resource while also defining the scope of the operation. It is clearly distinguishable from sibling tools like restore_snapshot or list_snapshots. The description is not a tautology of the tool name.

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 provides practical usage context: it is non-blocking by default, the agent should poll with snapshot_status, and confirm=true plus writes-enabled are required. It clearly covers when to invoke it and what to do after invocation, though it does not explicitly discuss alternatives or exclusions relative to sibling snapshot tools. This is clear and actionable context.

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