veto_drift_check

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

Annotations declare readOnlyHint=true, and the description confirms it queries a trace and calls the debugger agent. The call could be interpreted as a side effect, but the description frames it as formulating a plan, not mutating state. No contradictions, and additional behavioral detail is provided.

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?

Single sentence that efficiently front-loads the purpose ('Compounding-error checkpoint') and concisely explains the two main actions. No redundant or filler content.

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?

For a tool with no output schema, the description adequately explains inputs (trace) and output (remediation plan). The three optional parameters are self-explanatory from the schema. The description could be slightly more detailed about the return structure but is sufficient.

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% with descriptive parameter comments. The description does not add any parameter-specific guidance beyond the schema. Therefore, the baseline of 3 is appropriate.

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 uses specific verbs ('queries', 'calls') and identifies the exact resource (session's tool execution trace) and outcome (detect loop indicators, formulate remediation plan). It clearly distinguishes from sibling tools, none of which share this precise function.

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 description implies use as a 'compounding-error checkpoint' when loops or failures are suspected. However, it does not explicitly state when to avoid using it or mention alternative tools for similar diagnostics. The context is clear but lacks exclusions.

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