xlsx_data_clean

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

Discloses key behaviors beyond annotations: informer-not-enforcer pattern (findings for accept/reject/override), diagnose vs execute modes. Annotations show destructiveHint=false and readOnlyHint=false, but description contextualizes mutation with user consent, adding valuable transparency.

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?

Two focused paragraphs: first describes functionality, second usage guidance. Every sentence adds value, no redundancy. Front-loaded with key actions.

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?

Given complexity (8 params, no output schema), description covers purpose, usage, behavior, and parameter context well. Missing details on return format (e.g., Finding structure) and file limitations, but sufficient for high-level understanding.

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 has 0% description coverage; description compensates by explaining mode, options, and workflow (diagnose/execute, findings, overrides) but does not explicitly detail each parameter or their types, leaving some interpretation to the schema. Still provides meaningful semantic context.

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 clearly states the tool's purpose: AI-native data cleaning for local .xlsx files, listing seven specific data issues it addresses. It explicitly distinguishes from siblings (e.g., xlsx_doctor, dedicated pipelines), making purpose unambiguous.

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?

Explicitly provides when to use (upstream messy xlsx for LLM/analysis) and when not to use (domain transforms, structural checks, uploads), with specific sibling alternatives, offering excellent guidance.

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