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

No annotations exist, so the description must disclose side effects and safety profile. 'Critic' and 'inspect' hint at a read-only analysis, but the tool never explicitly states whether it modifies the trace, whether it blocks or returns diagnostics, or what side effects it may have. For a monitoring tool this is a meaningful gap.

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 concise sentence with a clear label ('Introspective reasoning critic') followed by the task and purpose. Every word contributes; there is no filler or duplication of schema 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?

Despite having an output schema, the tool lacks annotation and parameter-semantics information. The description is too sparse to support correct invocation: it does not clarify how to populate the required arguments, what 'invariant drift' means in the schema context, or whether the operation is safe. The presence of nested objects and 0% schema coverage raises the burden, which the description fails to meet.

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%, and the description does not explain any of the three parameters (trace_history, current_step, invariants). 'Trace in-flight' loosely maps to trace_history, but the agent receives no guidance on how to structure invariants or current_step, leaving the nested object schemas completely unexplained.

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 states a specific verb ('inspect'), a clear resource ('trace in-flight'), and the exact anomalies it detects ('cycles, invariant drift, vacuous output, and stalling'). This distinguishes it from sibling tools like inspect_self_model or verify_strategy, which target different objects, even without naming them.

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 phrase 'inspect trace in-flight' implies the tool should be used during an active reasoning trace, and 'to catch' lists concrete trigger conditions. However, there is no explicit when-to-use vs. when-not-to-use guidance, nor any mention of alternative tools like verify_strategy or inspect_self_model.

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