ag_table_csv_to_json

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

With no annotations, the description carries the behavioral burden. It discloses determinism, fixture verification, free guest usage with rate limits, the need for an api_key for member budget, and the return of a provenance envelope. It does not mention error handling for malformed CSV but covers the main behaviors.

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 mostly concise and front-loaded, but repeats 'Deterministic' twice and includes an embedded JSON schema that partially duplicates input schema details. Still, the extra schema provides useful payload validation context.

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 output schema exists and the description adds important context about the provenance envelope and usage limits. It does not detail error behavior, but the combination of output schema and description is sufficient for an agent to understand what the tool returns and when to use it.

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 itself provides no descriptions, but the description compensates by defining the payload fields csv, delimiter, and has_header, including auto-detection and header optionality. api_key is also mentioned in the rate-limit context. Slight ambiguity remains about delimiter override semantics.

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 verb 'Parse' and identifies the resource as CSV/TSV text, with the output being JSON row objects. It also distinguishes this tool from model-based parsing and from JSON-to-CSV 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 description provides usage context by calling it a deterministic alternative to model-based table reading and explains rate-limit/free-tier behavior with api_key. It does not explicitly contrast with ag_table_json_to_csv or ag_table_markdown_extract, but the core usage guidance is present.

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