Pick and reorder CSV columns by name or 1-based index. Handles quoted fields; emits csv, json, or markdown.
| Name | Required | Description | Default |
|---|---|---|---|
| csv | Yes | CSV text | |
| output | No | csv (default) | json | markdown | |
| columns | No | Column names or numbers, in output order (default all) | |
| delimiter | No | Single char (default ,) | |
| has_header | No | First row is a header (default true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It adds value by stating that it 'handles quoted fields' and 'emits csv, json, or markdown', which informs the agent about input robustness and output behavior. It does not mention side effects (likely none) but this is a read/transform tool; adequate for the context.
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 sentence that packs essential information: purpose, key capabilities (handle quoted fields, output formats). No filler or redundant content. Well-structured and front-loaded.
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 tool is moderate complexity with 5 parameters and no output schema. The description covers the core functionality but omits details like what happens with missing headers, how to specify columns by name vs. index, or potential errors. With no annotations and no output schema, a bit more detail would be helpful, but the schema provides full parameter documentation, so it is adequate.
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 the schema describes all parameters. The description adds some context (e.g., ability to reorder by name/index, output formats), but does not elaborate on parameter syntax (e.g., how to specify columns) beyond what the schema already provides. Meets the baseline of 3 given high schema coverage.
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 a specific verb ('Pick and reorder') with a clear resource ('CSV columns'), and mentions the key options (by name or index, output formats). It clearly distinguishes from siblings like 'csv_to_markdown' by focusing on column selection/reordering and multiple output formats, though it doesn't explicitly name the alternative.
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 implies usage for selecting/reordering columns and specifying output format, but does not explicitly state when to use this tool over alternatives like csv_to_markdown. It provides no when-not-to-use conditions (e.g., if needing only conversion, use csv_to_markdown). Guidance is minimal but not misleading.
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 are clearly distinct, but there is overlap between local ops tools (gbrain_get/list/search, host_memory_get/set, forge_loop_status, list_mesh_snapshot, etc.) and public status/product tools (forge_status, popular_tools) which could confuse an agent. Descriptions help by tagging local ops, but the boundaries remain blurred.
All tool names use snake_case and mostly follow a verb_noun or noun_verb pattern (e.g., get_product, list_live_products, csv_to_markdown). A few names like now_iso and lorem_ipsum deviate from the verb-first style, but overall the naming is predictable and consistent.
With 40 tools, the server is overloaded for a coherent set. Many are simple utility functions that could be consolidated, and the mix of generic utilities, product APIs, and local ops adds unnecessary bulk, pushing the count well above the comfortable range.
The server lacks a clear domain, making it impossible to assess lifecycle coverage. While it offers many utilities, there is no coherent surface—missing common operations for any single category (e.g., no CRUD, no file handling) and many tools feel randomly assembled rather than forming a complete workflow.