parse_csv_and_suggest

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

With no annotations, the description states the tool does not write data, revealing its read-only nature. While it could detail error handling or output format, the non-destructive guarantee is well communicated.

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 sentences, front-loaded with purpose, second with usage guidance. Every word earns its place with no redundancy.

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?

Adequately covers the tool's role as a first-call read-only analysis. Missing details about output format (e.g., suggested fields and rules) leaves the agent uncertain about next steps, especially given no output schema.

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 a single parameter 'csv_text' already described in the schema. The description adds 'product/offer CSV' context, but this is marginal improvement, warranting baseline 3.

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 parses a product/offer CSV, infers XDM types, and suggests schema fields, eligibility rules, and ranking formulas. This specific verb+resource combination differentiates it from sibling tools, none of which parse CSVs.

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 says 'Always call this first — no data is written.' This provides clear when-to-use context and distinguishes it as a non-destructive pre-processing step before other mutation tools.

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