get_diagnostics

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

With no annotations, the description carries the full burden, and it does deliver the single most important behavioral fact: the probabilities are teacher-forced rather than sampled/generated. It says nothing about read-only safety, permissions, or the two-level pagination behavior, and an output schema means return shape needn't be restated.

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?

A single front-loaded sentence with zero filler and the key caveat placed prominently. It is efficient, though the terseness borders on under-specification given the parameter confusion it leaves unaddressed.

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?

An output schema covers return values, but a six-parameter tool with two nested paging mechanisms and no annotations gets no explanation of its parameters or when to prefer it over sibling retrieval tools. The definition is only partially sufficient for correct invocation.

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% across six parameters, so the description must compensate and it largely does not. It implies why top_k_limit/top_k_offset exist (token probabilities) but explains nothing about run_id, case_id, limit, or offset, nor how the outer limit/offset paging relates to the inner top_k paging.

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?

Names a concrete resource and operation: paging through teacher-forced token probabilities, plus an explicit negative scope (not generated task outcomes). An agent can tell what it will get, though the description never mentions run_id/case_id scoping or distinguishes this from siblings like get_inspection or get_capture.

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?

There is no explicit when-to-use guidance and no named alternative. The clause 'these are not generated task outcomes' implicitly tells the agent what this tool is NOT for, but it does not route to the tool that does return generated outcomes, leaving selection largely to inference.

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