Read-only file metadata operations on Quadratic files the user has access to. No data is modified. Requires authentication.
Actions: • list_files() — List all accessible files. • get_file_info(file_id) — Get metadata for a single file.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Action to perform: list_files or get_file_info | |
| params | No | Parameters for the action (see tool description) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is known. The description adds 'No data is modified' and 'Requires authentication,' which are useful behavioral details not covered by annotations. It also enumerates the exact actions, providing clarity on what the tool does beyond the hints.
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 compact and well-organized: a top-line purpose statement, then a bulleted list of actions. Every sentence or bullet adds distinct value, with no redundant content or filler.
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 simple metadata tool with two actions, the description is largely complete given the read-only and idempotent annotations. It lacks return-value details and parameter types/formats, but the absence of an output schema and the low complexity keep this from being a major gap. The description sufficiently supports correct invocation.
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?
The input schema provides only a generic 'params' object with a note to see the tool description. The description compensates fully by specifying the two actions and their parameters: list_files() takes no params and get_file_info(file_id) takes a file_id. This is essential meaning that the schema lacks, giving the agent the information needed to invoke the tool correctly.
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 opens with a clear statement: 'Read-only file metadata operations on Quadratic files the user has access to.' This uses a specific verb ('read'), resource ('file metadata'), and scope ('user has access'), and the read-only qualifier distinguishes it from the sibling files_write. The two listed actions further clarify the exact operations.
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 states it is for read-only metadata and requires authentication, giving clear context for when to use it. However, it does not explicitly mention alternatives like read_data or exclude content reads, so the differentiation from sibling tools is implicit rather than direct.
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 clearly distinct concern: auth handles session lifecycle, files_read lists metadata, files_write manages file sessions, read_data queries spreadsheet contents, and write_data modifies them. No two tools have overlapping purposes.
Tool names follow inconsistent conventions: 'auth' is a bare noun, 'files_read' and 'files_write' use noun_verb order, while 'read_data' and 'write_data' use verb_noun order. This mixed pattern makes it harder to predict related tool names.
Five top-level tools form an elegant umbrella structure that groups dozens of actions into meaningful categories. The count is ideal for guiding an agent to the correct tool without overwhelming it.
The surface covers the full spreadsheet lifecycle: authentication, file management, cell/range operations, formulas, code, SQL, formatting, sheets, tables, charts, pivot tables, validation, and history. Missing file deletion/rename and some advanced sheet management are minor gaps that can be worked around.
