inspect_csvReturn record, maximum column and cell counts with up to 20 preview records. Preserve ragged and empty records; never infer types or a delimiter.
| Name | Required | Description | Default |
|---|---|---|---|
| csv | Yes | Complete UTF-8 CSV text, up to 256 KiB. All cells remain strings; formulas are never evaluated. | |
| delimiter | No | Explicit delimiter; no delimiter inference. | , |
| previewRows | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety bar is prefilled. The description still adds real behavioral context beyond them: ragged and empty records are preserved rather than normalized, and no type or delimiter inference occurs. It doesn't say how counts are computed or how the preview is truncated (head vs. sample), which keeps it below 5.
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?
Two sentences, both front-loaded with the highest-value facts (what is returned, then the fidelity guarantees). No filler or restatement of the title.
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?
No output schema exists, so the description must sketch the return shape — it does (counts plus up to 20 preview records). For a 3-parameter read tool with full annotations and a well-documented schema this is close to sufficient; only the exact meaning of 'maximum cell counts' and preview ordering remain unstated.
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 67% and the schema itself documents csv (256 KiB limit, all cells strings, formulas not evaluated) and delimiter (explicit, no inference). The description echoes the delimiter/no-inference contract and the 20-record preview cap, but adds little on the csv parameter and nothing on previewRows=0 behavior. Baseline 3 is appropriate when the schema carries most of the detail.
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 and resource set: return record/column/cell counts plus preview records. That clearly separates a read-only inspection from the mutating siblings (edit_csv_cells, filter_csv_rows, sort_csv_rows). It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.
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 purpose implies usage — profile a CSV before editing/filtering/sorting it — but the description never says when to prefer this tool over its siblings or what conditions rule it out. Guidance is inferable rather than stated.
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.