floot

Read Files

read_files

Read-only

Read MULTIPLE files from a Floot project in ONE call — much cheaper than repeated read_file (the whole project is loaded once, one round-trip). Prefer this whenever you need several files together (e.g. an endpoint + its .schema.ts + the hook that calls it, or orienting in a feature). Pass up to 20 paths (same item scheme as read_file; /_cdn/ asset paths are accepted too and images come back as image blocks). Each file is returned cat -n style under a header. Reads do not typecheck by default: diagnostics:"auto" appends each .ts/.tsx file's current type errors when the compute VM is warm, "wait" forces the check. include_references:true appends each file's referencing files (same analysis as read_file). Output is capped overall; if the batch is too large, whole files at the end are omitted and listed by name so you can read them individually. With older_than (up to 5 paths) the files are walked back through history TOGETHER on one timeline — the way to keep a component and its stylesheet consistent.

Input Schema

Name	Required	Description
`limit`	No
`paths`	Yes
`projectId`	Yes
`older_than`	No	Omit (or leave empty) to read the current file. Set it only to read the file as it was BEFORE an earlier change. Pass "current" for the version just before the latest change to it, then the cursor each result gives you to step one change further back — until you find a good version, then write it back with write_file (or merge by hand). Not a version number: each step is one recorded change to the file. Type errors and references are skipped for past versions.
`diagnostics`	No
`include_references`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 29, 2026

changedInput schema / properties / older_than / description

Previous value: -"Read the file as it was BEFORE an earlier change instead of the current file. Pass \"current\" for the version just before the latest change to it, then the cursor each result gives you to step one change further back — until you find a good version, then write it back with write_file (or merge by hand). Not a version number: each step is one recorded change to the file. Type errors and references are skipped for past versions."New value: +"Omit (or leave empty) to read the current file. Set it only to read the file as it was BEFORE an earlier change. Pass \"current\" for the version just before the latest change to it, then the cursor each result gives you to step one change further back — until you find a good version, then write it back with write_file (or merge by hand). Not a version number: each step is one recorded change to the file. Type errors and references are skipped for past versions."

Changed1 schema field changedSep 29, 2026

addedInput schema / properties / older_than

Added value: +{
+  "description": "Read the file as it was BEFORE an earlier change instead of the current file. Pass \"current\" for the version just before the latest change to it, then the cursor each result gives you to step one change further back — until you find a good version, then write it back with write_file (or merge by hand). Not a version number: each step is one recorded change to the file. Type errors and references are skipped for past versions.",
+  "type": "string"
+}

Changed1 schema field changedSep 1, 2026
- addedInput schema / properties / include_references
```
Added value: +{
+  "type": "boolean"
+}
```
First observedAug 27, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a safe read (readOnlyHint=true, destructiveHint=false), but the description adds substantial non-obvious behavior: overall output capping with whole files omitted and listed by name, cat -n style rendering, image blocks for /_cdn/ assets, typecheck cost semantics for diagnostics ('auto' only when the VM is warm, 'wait' forces), and the shared-timeline semantics of older_than. This is well beyond annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical point (batch read, cheaper than repeated read_file) is front-loaded in the first clause. The remainder is dense and every sentence carries new information, though the single run-on paragraph with heavy em-dash use makes it harder to scan than it could be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description covers return format (headers, cat -n style, image blocks) and truncation behavior, plus the diagnostics/references/older_than side effects. For a 6-parameter tool with sparse schema descriptions, nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 17%, so the description carries the burden and mostly does: it explains paths (up to 20, read_file item scheme, /_cdn/ asset paths), older_than (up to 5 paths, walked back together on one timeline, not a version number), diagnostics (auto vs wait) and include_references. It omits the 'limit' parameter and the 'off' enum value, leaving a small gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with explicit scope ('Read MULTIPLE files ... in ONE call') and distinguishes itself from the sibling read_file by naming it and stating the cost advantage. An agent can tell immediately this is the batch variant of read_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Prefer this whenever you need several files together' gives an explicit selection rule, reinforced with concrete scenarios (endpoint + .schema.ts + hook, orienting in a feature). The alternative (repeated read_file) is named and the condition that favors this tool is stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All floot tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?