start_csv_profiling

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

No annotations are provided, so the description carries the full burden. It does not disclose side effects, performance impact, whether a background process is started, how to stop it, or what happens to existing captures. The meaning of 'capture' is vague and lacks operational detail.

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?

The description is a single, front-loaded sentence with no redundant words. It conveys the essential action and purpose efficiently.

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?

The tool is simple with one optional parameter and no output schema, but the description omits critical context: how to stop the capture, whether it returns any data, and what side effects (e.g., file creation, performance overhead) occur. The existence of sibling stop_csv_profiling makes the lack of lifecycle guidance a notable gap.

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?

The input schema covers 100% of the parameter (filename) with a description, so the baseline is 3. The tool description itself adds no extra parameter information, but the schema sufficiently documents the optional filename.

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 a specific action: 'Start CSV profiling capture' with a purpose ('for performance regression analysis'). It uses a specific verb and resource, distinguishing it from general start_trace, though it doesn't explicitly contrast with sibling tools.

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 'for performance regression analysis' provides context on when to use the tool, but there is no explicit guidance on when not to use it or mention of alternatives like stop_csv_profiling or start_trace. The usage is implied rather than clearly scoped.

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