Release an advisory lock you own on a path.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to unlock, relative to the workspace root. Must be a lock this token holds. | |
| workspace | No | Workspace slug. Optional, defaults to "temp". |
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 idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds the crucial ownership constraint and clarifies this is an advisory lock, which informs the agent about preconditions and lock semantics.
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?
Single sentence that is front-loaded with the action and resource, with no redundant words.
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 two-parameter tool with full annotations and no output schema, the description provides the essential purpose and precondition. It could mention failure behavior, but the provided context is sufficient for selecting and invoking the tool.
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%, with detailed descriptions for both path and workspace. The tool description itself adds no parameter-specific meaning beyond the schema, so baseline 3 applies.
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 uses a specific verb ('Release') and identifies the resource ('an advisory lock you own on a path'), clearly distinguishing it from sibling tools like lock (acquire) or delete.
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 is for releasing locks the caller owns, but does not explicitly state when to use it versus lock or what to do if the lock is not owned. Context is present but no exclusions or alternative references.
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 distinct operation: file CRUD (write, read, edit, delete), versioning (history, restore), search (grep, list with q), locking (lock, unlock), uploads (request_upload, finalize_upload), and activity tracking. Even similar tools like request_upload and finalize_upload are complementary rather than overlapping.
Tool names are lowercase and action-oriented, with single-word verbs (read, write, delete) and two compound verbs (request_upload, finalize_upload) following a verb_noun pattern. This is consistent enough to be predictable, though the mix of single words and compound words is a minor deviation.
14 tools is well-scoped for a versioned file management server. Each tool covers a necessary aspect of the domain—file operations, version control, search, locking, uploads, and activity—without unnecessary bloat or missing critical functionality.
The tool set covers the full lifecycle of file management: create/write, read, edit, delete, restore, list, search, lock, unlock, upload/download (via request_upload/finalize_upload and read's download URL). The only potential gap is a copy operation, but that can be achieved with read+write. All workflows have no dead ends.
