parse_table

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: auto-detection behavior ('most frequent candidate on the first line is chosen and reported back') and the RFC 4180 conformance guarantee. It doesn't mention behavior at row-cap truncation, which would be the last missing piece.

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?

Three sentences, each earning its place: capability, auto-detection behavior, and the routing contrast. The most important distinguishing information (RFC 4180 and the anti-pattern warning) is front-loaded. No filler.

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 read-only, idempotent parse tool with no output schema, the description covers purpose, edge cases, auto-detection, and routing. The only gap is that it doesn't describe the shape of the returned header/rows structure, which matters somewhat since there's no output schema. Still, the RFC 4180 reference implies a standard table structure an agent can reason about.

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%, so all four parameters are already documented with defaults and ranges. The description reinforces auto-detection semantics for the delimiter parameter, which is genuinely useful added meaning, but does not add syntax or format detail for text, maxRows, or hasHeader. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb (Parse) and resource (delimited text into header plus rows), and goes further by enumerating the exact edge cases handled (quoted fields, escaped quotes, embedded delimiters, embedded newlines, RFC 4180). This distinguishes it clearly from siblings like regex_extract or convert, which are the nearest overlap candidates.

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 when to use it versus the naive alternative: 'Use instead of splitting on commas, which breaks on any real CSV.' This names the anti-pattern and the reason, giving the agent a clear routing rule without needing to guess.

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