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?
The description discloses the transformation behavior (detect, repair, re-emit) beyond what annotations provide. It also indicates the output format (UTF-8 with BOM). Annotations already declare read-only and non-destructive, so the description adds meaningful context about the specific processing steps.
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 two sentences, front-loaded with the core action, and every part adds value: encoding types, mojibake examples, and the BOM detail. No filler or redundant information.
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 description covers the main functionality and expected input/output. It does not mention that one of two parameters must be supplied, nor does it clarify asynchronous behavior (sibling check_job suggests possible job-based execution), but the output schema exists and the core behavior is well-explained.
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 both 'url' and 'text' described, so the baseline is 3. The description implies these are two alternative input methods ('Detect... and re-emit' doesn't add new parameter meaning), but it doesn't clarify that at least one is needed. No additional semantic value is added beyond the schema.
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's function: detect real encoding, repair mojibake, and re-emit UTF-8 with BOM. The verb 'repair' and specific resource 'CSV' make it distinct from sibling tools, which are largely PDF-related.
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 provide clear context: use when a CSV opens garbled in Excel. It doesn't explicitly mention alternatives or exclusions, but the use case is unambiguous. Since there are no closely related CSV tools (except csv_to_qbo, which serves a different purpose), this is sufficient.
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.
Each tool targets a unique operation—conversions, extractions, translations, and utilities like resume checking or redaction—with no meaningful overlap. The few similar tools (e.g., convert_to_pdf vs. xlsx_to_pdf) are clearly distinguished by input type.
Naming mixes conventions: verb_noun (extract_tables, redact_text), noun_to_noun (xlsx_to_pdf, pptx_to_pdf), and unusual forms like doc_translate_cn and what_can_you_do. While snake_case is consistent, the verb/noun pattern is not, making the set slightly less predictable.
With 23 tools, the server sits at the heavy end of the acceptable range. Every tool has a distinct purpose, but the spread across PDF handling, research, audio, and accounting utilities feels more like a miscellaneous collection than a focused suite, which could overwhelm agents.
The server covers a broad spectrum of document-processing tasks—conversion, extraction, translation, redaction, and validation—with few dead ends. Minor gaps exist (e.g., no PDF merge/split, no OCR for all scanned PDFs, no explicit delete/update for resources), but core workflows are well supported.