bgi_watch

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

With no annotations, the description carries the burden and does well: it declares read-only, repeatability, the 50s polling cap, and crucially that only current-run ERRs count as failures while earlier-run ERRs are listed separately. Missing only return-format details.

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?

Dense, front-loaded, and no filler; the read-only/repeatable nature and polling caveat are stated up front. Packed but readable.

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?

No output schema exists, and the description compensates by explaining the verdict states and ERR scoping. Largely complete for an agent to call and interpret it, though return shape is only partially sketched.

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 parameters are already documented; the description reinforces wait_seconds' single-call polling semantics and the verdict=incomplete behavior. Baseline 3 is appropriate since the schema does the heavy lifting.

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+resource: observe and judge success/failure of a run, plus read-only and repeatable nature. Distinguishes itself implicitly from siblings like bgi_status and bgi_results, though it doesn't name them explicitly.

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?

Explains default immediate return, that verdict=incomplete means polling again later, and that wait_seconds polls up to 50s in a single call. Clear operational guidance, though no explicit 'use X instead' routing to siblings.

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