Skip to main content
Glama

Preview a delegate (free)

kimi_delegate_dry_run
Read-only

Preview a Kimi delegation's scope and cost without spending: see baseline repo, prompt size, and workspace isolation, then confirm before committing to the paid call.

Instructions

Preview what a kimi_delegate/kimi_delegate_async call would do — the baseline it seeds from (HEAD commit, tracked file count/size, uncommitted and untracked counts), the prompt size that would be sent, and the resolved workspace/isolation. Free — no model call, no spend, no worktree created.

Use it before delegating to confirm scope and repo before committing to cost, exactly as kimi_dry_run previews kimi_review_changes. Mirrors the real delegate's zero-spend validation (workspace, isolation, task size, git repo), so a failure here is a failure the paid call would also hit. The returned tier/sandbox describe the previewed propose run, not this read-only preview; the result echoes the effective model/reasoning_effort overrides the paid call would send (unvalidated). deadline_advisory is non-null when size or reasoning effort risks the synchronous deadline and names kimi_delegate_async verbatim — the async counterpart of the previewed call, not of this dry-run tool. A hint, not a refusal.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesThe coding task you want Kimi to implement via a real kimi_delegate call; this dry run only previews the seeded baseline and prompt size — it does NOT call Kimi or return a diff. Must be non-blank: empty or whitespace-only is rejected here too, not previewed.
modelNoThe Kimi model slug the previewed paid call would use; defaults to the server default (MOONBRIDGE_MODEL) when unset, so the preview mirrors the paid call's resolution. This dry run does not call Kimi or validate the model.
isolationNoKimi skills isolation: which skills Kimi loads — 'inherit' (its own user/project discovery) or 'ignore-skills' (replace those with an empty directory). Kimi's built-in skills load either way. Defaults to the server's configured value (built-in 'inherit'; `kimi_status` reports the resolved one).
workspace_rootNoAbsolute path to the target repo root — pass it (or an MCP root) to target the intended repo; otherwise the call falls back to the server's own cwd and sets meta.workspace_warning.
reasoning_effortNoThe reasoning effort the previewed paid call would send (as a `model_reasoning_effort` config override); defaults to the server default (MOONBRIDGE_REASONING_EFFORT) when unset, so the preview mirrors the paid call's resolution. This dry run does not call Kimi or validate the value beyond the paid params' shape bounds (no control or surrogate characters, ≤128 chars).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes
Behavior5/5

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

Annotations declare readOnlyHint=true, and the description reinforces with no-spend/no-worktree/no-model-call details. It goes beyond annotations by clarifying the returned tier/sandbox refer to the previewed run, that model/reasoning_effort echoes are unvalidated, and that `deadline_advisory` is a hint, not a refusal. This is rich behavioral disclosure.

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 description is one dense paragraph but every sentence earns its place, covering purpose, side-effects, analogies, and disambiguation of output fields. It is slightly long and could be split for readability, but it's well-structured and front-loaded with the core purpose.

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?

Despite having an output schema, the description adds essential context about no side effects, validation mirroring, and subtle output semantics (tier/sandbox, overrides, deadline_advisory). It clearly positions the tool among its many siblings and covers the complex behavioral nuances, making it complete for safe agent use.

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

Parameters3/5

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

Schema description coverage is 100%, and the schema provides thorough per-parameter explanations. The tool description itself doesn't add parameter-specific meaning, but it doesn't need to; the baseline of 3 applies because the schema does the heavy lifting.

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 a specific verb+resource: 'Preview what a kimi_delegate/kimi_delegate_async call would do' and lists concrete preview contents (baseline, prompt size, workspace/isolation). It also distinguishes from the sibling dry_run tool by explicit analogy: 'exactly as kimi_dry_run previews kimi_review_changes'.

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?

Explicit when-to-use guidance is given: 'Use it before delegating to confirm scope and repo before committing to cost.' It also names the alternative and clarifies the validation mirroring, so the agent knows failure here predicts failure in the paid call. It further explains that `deadline_advisory` points to the async counterpart, not this tool.

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/briandconnelly/moonbridge'

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