files_putStore a file and get a URL for it — a report, a CSV, a transcript
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | File name including its extension, e.g. "report.csv" | |
| type | No | Optional content type, e.g. "text/csv". Guessed from the name when omitted | |
| content | Yes | The file's contents — plain text, or base64 when encoding is "base64" | |
| encoding | No | "base64" for binary files; omit for text |
Changes observed during successful MCP inspections.
Input schema / properties / content / descriptionPrevious value: -"The file's contents — plain text, or base64 when encoding is base64"New value: +"The file's contents — plain text, or base64 when encoding is \"base64\""Input schema / properties / name / descriptionPrevious value: -"File name including its extension, e.g. report.csv"New value: +"File name including its extension, e.g. \"report.csv\""Input schema / properties / type / descriptionPrevious value: -"Optional content type, e.g. text/csv. Guessed from the name when omitted"New value: +"Optional content type, e.g. \"text/csv\". Guessed from the name when omitted"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses only the basic behavior (storing a file and returning a URL). Since no annotations beyond the title are provided, it does not disclose potential behavioral traits such as error handling, overwrite semantics, access permissions, size limits, or whether the file is publicly accessible. This is a significant gap for a mutation tool with no annotation support.
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, front-loaded sentence that delivers the core purpose and one key detail (URL return) without extraneous information. The examples are compact and add value without bloat, making it highly concise and well-structured.
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 is adequate for a simple store operation: it explains the return value (URL) and the schema covers parameters. However, there is no output schema, and the description omits any discussion of edge cases, error conditions, or operational constraints (e.g., file name collisions, binary encoding implications), which leaves the tool only partially complete for an agent to use confidently.
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 100%, so the schema fully documents all four parameters (name, type, content, encoding). The description adds no additional semantic meaning beyond what the schema already provides, though it does reinforce the intended use case. This aligns with the baseline score of 3 when schema coverage is high.
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 a specific action (store a file), the resource (files), and the key outcome (get a URL). It includes concrete examples (report, CSV, transcript) that illustrate typical use cases, and it is easily distinguishable from sibling tools like files_delete, files_get, files_list, and files_share.
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 ('Store a file and get a URL'), making it clear when to use it for uploading files. However, it does not provide explicit guidance on when to choose this over alternatives or mention any exclusions, prerequisites, or scenarios where another tool (e.g., files_share) would be more appropriate.
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.