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

Goes well beyond the readOnly/idempotent annotations: short-lived nonce, opaque check_id, the probe never being admitted, not metered, and the crucial rule that a transfer-service failure reports data_channel_unavailable rather than incapable. That last point prevents a serious misread of results.

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?

Front-loaded with the purpose, then the call protocol, then the status/error semantics. Dense but every sentence carries information an agent needs to interpret a verdict correctly.

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?

Output schema covers return shape, and the description supplies the state machine (pending/capable/incapable) plus the error carve-out. Nothing an agent needs in order to call or interpret it 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?

Schema coverage is 100% and the oneOf branches are structural, but the description adds the semantic role of each mode (start vs. verdict read) and that idempotency_key replays return the same probe. It doesn't explain format bounds (8-128 chars), which the schema already handles.

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?

Opens with a specific verb+resource: proving whether the host can execute FinStat's signed HTTPS upload program. The framing as a capability probe (temporary, never admitted) distinguishes it from sibling tools like create_upload_sessions, which do real transfers.

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?

Explicit two-mode call contract: start with workspace_tag + idempotency_key, then call again with check_id to read the verdict. It also states that exact replay of the start is safe, so the agent knows how to poll without ambiguity.

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