Provision (or re-provision) a sandbox for a PR. Wraps pr-sandbox.provisionSandbox. Requires 'repo' scope. Returns {ok:false, reason:'not enabled on this host'} when no sandbox provisioner runs on the host.
| Name | Required | Description | Default |
|---|---|---|---|
| repo | Yes | ||
| owner | Yes | ||
| number | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate the tool is not read-only (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds value by disclosing the internal wrapper (pr-sandbox.provisionSandbox), an auth requirement ('repo' scope), and a specific error return when the host lacks a provisioner. This contextualizes behavior beyond annotations.
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 three sentences (45 words) and front-loaded with the primary purpose. The second sentence adds implementation context, and the third covers a key error case. No filler or redundant information. Every sentence contributes meaningfully.
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?
Although the tool is simple with three clear parameters and no output schema, the description does not specify the success return value or side effects. It only documents the failure case. Annotations cover destructive intent, but the description omits whether provisioning creates resources or has any rate limits. Adequate but not fully thorough for a mutation 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 0%, so the description carries the burden of explaining parameters. The parameter names (repo, owner, number) are standard and self-explanatory for a PR sandbox tool, but the description does not explicitly define them, their formats, or constraints. For example, it does not confirm that 'number' is the PR number or clarify that 'repo' and 'owner' are GitHub identifiers.
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 the tool provisions or re-provisions a sandbox for a PR. The verb 'provision' and resource 'sandbox for a PR' are specific and distinct from sibling tools like create_pr, merge_pr, or get_pr. The mention of wrapping an internal function adds clarity without ambiguity.
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 mentions a prerequisite ('Requires repo scope') but provides no explicit guidance on when to use this tool versus alternatives. While no other tool provisions sandboxes, the description could clarify scenarios (e.g., after PR creation) or when re-provisioning is appropriate. The 'or re-provision' hint is mild guidance.
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.
Several tools have near-identical purposes, such as `gluecron_read_file` and `gluecron_repo_read_file` (both read a file from a repo), and `gluecron_explain_repo` and `gluecron_repo_explain_codebase` (both return cached AI explanation). This creates ambiguity despite minor differences in description. While many tools are distinct, the overlapping pairs force an agent to choose between effectively equivalent operations, lowering disambiguation.
All tools use the `gluecron_` prefix followed by a verb_noun pattern (e.g., `acquire_lease`, `create_issue`, `merge_pr`). A few tools like `gluecron_ai_cost_summary` and `gluecron_repo_explain_codebase` deviate slightly but remain readable and predictable. Overall, the naming convention is largely consistent, making it easy to infer tool function from the name.
With 60 tools, the server far exceeds the 25-tool threshold for 'too many' per the guidelines. Although the server covers a broad developer platform (repository management, issues, PRs, workflows, AI features, etc.), the sheer number of tools makes navigation heavy and risks overwhelming both agents and users. A more focused set would improve coherence.
The tool set is remarkably thorough, covering nearly every lifecycle stage for repositories, issues, pull requests, workflows, branches, commits, and AI-assisted features (chat, test generation, release notes, refactoring, voice-to-PR). Essential CRUD operations are present, and advanced operations like leasing, sandbox provisioning, and multi-repo refactoring are included. There are no obvious gaps for the stated purpose of a developer platform.
