export_csv

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

With readOnlyHint=false and destructiveHint=false, the annotations alone would leave an agent guessing about side effects. The description resolves this with crucial safety disclosures: 'Never overwrites an existing file and never touches the schedule,' and explains the full dry_run contract ('returns the row count, columns and first rows without writing') plus the configuration gate for real writes (allow_writes=true in longpath.toml). This is exactly the behavioral context that matters for a file-writing tool.

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 that are information-dense but earn their length. The purpose is front-loaded, the long tool enumeration is necessary because the schema provides no enums, and the dry_run/write mechanics are essential for a two-phase tool. It is on the verbose side, but no sentence is wasted.

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 wrapper tool with no output schema, no enums, and 0% schema coverage, this description carries nearly the full burden and succeeds: it covers the source-tool contract, safety properties, dry_run return shape, and the prerequisite configuration for writing. The only real omission is the return value of a successful actual write (only dry_run's return is described).

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 description coverage is 0% and there are no enums, so the description must compensate entirely — and it does. It enumerates valid values for `tool`, explains that `arguments` are 'that tool's arguments (path, filters...)', and details `dry_run` behavior. The only slight gap: `csv_path` is implied by 'to a new .csv file' but never explicitly defined as the output file path.

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 opens with a specific verb+resource pair: 'Write the FULL list behind one of the list tools to a new .csv file (Excel-friendly UTF-8).' This clearly distinguishes it from its siblings, which are all read/analysis tools that return data rather than write files. It also adds the scope qualifier 'FULL list' and 'never touches the schedule,' making its role 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?

The description lists all 11 compatible source tools and flags the special argument requirements for some (check=..., section=...), giving practical guidance on when this tool applies. It also conveys the two-step usage pattern: default dry_run first, then dry_run=false with allow_writes=true for actual writing. It stops short of an explicit 'use X instead when...' statement, but since no sibling writes CSV files, the alternative-avoidance question is effectively answered.

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