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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false. The description adds meaningful behavior beyond those annotations: existing content remains available until the refresh succeeds, including for live published sources, and duplicate work is risked if a new request key is used.

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 compact and front-loads the core purpose before the request-key behavior. The second sentence is dense and somewhat awkward in phrasing, but every clause carries useful information.

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 rich annotations, full schema description coverage, and an output schema, the description provides the essential behavioral context: old content survives until success and request keys prevent duplicate work. It does not explain exactly what refresh re-fetches or how operation status should be tracked, but the output schema and source_operation_read sibling reduce that gap.

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 agent_id and source_id are already well documented. The description adds extra semantic meaning for request_key by explaining that it identifies identical replays or source_operation_read checks and that a new key risks duplicate work.

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 refreshes an owned usable source and adds the important scope that old content serves until success, including live published sources. It is a specific verb+resource, though it does not explicitly distinguish refresh from source_read, source_text_revise, or source_operation_read beyond the retry key note.

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?

Usage is implied through the note that old content continues serving until success and that identical retries should reuse the client-generated key. However, it does not explicitly say when to choose source_refresh versus source_read, source_operation_read, or source_text_revise, nor does it state when not to use refresh.

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