Skip to main content
Glama

delete_files

Batch-delete up to 500 files by ID in one call; per-ID failures are isolated and reported, partial success supported. Use list_files to preview before deleting.

Instructions

DESTRUCTIVE batch — delete up to 500 files by ID in one call. Same physical-deletion rules as delete_file (KB files unlinked from disk; project reference files only de-indexed). Per-ID failures isolated to errors[]; the batch keeps going — partial success is the norm. Not idempotent — unknown IDs surface as per-item errors. No external auth or rate limits. Returns {deleted_count, error_count, deleted, errors}. To preview the set before deleting, run list_files with the same filter and confirm the IDs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idsYesFile IDs to delete (max 500 per call)
Behavior5/5

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

With no annotations, the description carries full transparency burden. It discloses physical deletion rules (KB unlinked vs project de-indexed), per-ID error isolation, partial success, non-idempotency, and lack of auth/rate limits. This exceeds typical transparency.

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

Conciseness5/5

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

The description is dense but each sentence provides unique value: scope, deletion rules, error behavior, idempotency, auth, and preview guidance. The opening line front-loads the critical 'DESTRUCTIVE batch' warning.

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?

Given the simple single-parameter schema and no output schema, the description fully covers operation semantics, return format, error handling, and alternatives. There are no unanswered questions for an agent deciding to invoke it.

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 100% (the `ids` array is described as 'File IDs to delete (max 500 per call)'). The description adds behavioral meaning: unknown IDs become per-item errors, failures don't abort the batch, and returns a structured result. This enhances the bare schema.

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?

The description opens with 'DESTRUCTIVE batch — delete up to 500 files by ID in one call', clearly stating the verb, resource, and batch scope. It distinguishes itself from the singular `delete_file` sibling by emphasizing the batch nature and the 500-file limit.

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

Usage Guidelines4/5

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

It explicitly references `delete_file` for shared deletion rules and advises running `list_files` to preview before deleting, providing a concrete alternative. While it doesn't state 'use delete_file for a single file', the batch distinction is clear from the name and description.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/safiyu/kontexta'

If you have feedback or need assistance with the MCP directory API, please join our Discord server