fix_csv_encodingDetect the real encoding of a CSV (GB18030, Shift-JIS, Windows-1252…), repair mojibake (UTF-8 that was read as Latin-1, e.g. "é"), and re-emit UTF-8 with a BOM so Excel opens it correctly.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Public URL of the CSV. | |
| text | No | Or paste the CSV content directly. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds useful behavioral details: supported encodings, an example of mojibake, and the re-emission with a UTF-8 BOM. No contradiction with annotations.
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, focused sentence with front-loaded verbs and parenthetical examples. It conveys all essential information without waste.
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 tool with two parameters, annotations, and an output schema, the description is sufficiently complete: it explains purpose, behavior, and result. It could note that exactly one of url or text is required, but the schema already conveys both options.
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 descriptions cover both parameters (url and text) at 100%, so the description does not need to add extra parameter details. With high schema coverage, the baseline of 3 applies; the description provides no additional parameter-specific guidance.
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 uses specific verbs ('Detect', 'repair', 're-emit') and names the resource (CSV) and desired outcome (opens correctly in Excel). It clearly distinguishes from sibling tools like csv_to_json or clean_table by focusing on encoding repair.
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 title and description establish a clear use case: when a CSV opens garbled in Excel. However, it does not explicitly mention alternatives or state when not to use the tool, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct functions (conversions, cleaning, xlsx I/O, reconciliation), but diff_tables, reconcile_ledger, and match_transactions all involve comparing or matching records, which could cause initial confusion. However, each has a specific use case—generic column diff, amount-focused reconciliation, and keyless fuzzy matching—and the descriptions provide enough detail to disambiguate them.
The conversion tools follow a consistent 'csv_to_*' or 'json_to_csv' pattern, while operation tools use a verb_noun style (e.g., clean_table, merge_tables, reconcile_ledger). This dual pattern is predictable by function type, but 'what_can_you_do' breaks convention as a question-like meta-tool, so the naming is mostly consistent with a minor deviation.
With 15 tools, the server sits at the upper edge of the well-scoped range, but each tool earns its place in the CSV/spreadsheet domain—covering conversions, cleaning, merging, diffing, reconciliation, matching, and Excel I/O. The count feels appropriate for the server's broad yet focused scope.
The toolset covers the full lifecycle of table manipulation: reading (read_xlsx), encoding repair, cleaning and transforming (clean_table), merging (merge_tables), comparing (diff_tables, reconcile_ledger), matching without keys (match_transactions), entity deduplication, and output to various formats (JSON, MD, chart, QBO, XLSX). No obvious gaps are evident for common tasks.