Skip to main content
Glama

bx_analysis_submit

Idempotent

Prepares a project revision for LLM analysis and submits the completed JSON response for native Core validation and saving.

Instructions

默认host模式:prepare取完整规范,当前LLM分析后complete提交JSON,由原生Core计算保存;不需要额外模型API。 / DEFAULT HOST WORKFLOW: use profile_id host. action prepare freezes project/revision and returns instructions_artifact and preparation_sha256. Read ALL instruction pages, analyze with the current LLM, then action complete supplies response (full JSON text), job_id and preparation_sha256. Native Core validates and saves; poll bx_job_get and read result_revision. No extra API or server model call. Legacy API mode requires confirm_model_call:true and an explicit API profile.

Input Schema

NameRequiredDescriptionDefault
actionNo
job_idNo
responseNo
revisionYes
project_idYes
request_idYes
confirm_model_callNo
preparation_sha256No

Output Schema

NameRequiredDescriptionDefault
dataYes
kindYes
productYes
api_versionYes
business_decisionYes
execution_authorizationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0-rc.9-linux.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare the safety profile (mutating, idempotent, non-destructive, open-world); the description adds real behavioral context: prepare freezes project/revision, returns instructions_artifact and preparation_sha256, the current LLM does the analysis rather than a server model, and results arrive asynchronously via job polling plus result_revision. It does not cover failure behavior, what happens if prepare is repeated against a moved revision, or how request_id affects idempotency, which keeps it short of a 5.

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

Conciseness3/5

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

The content is dense and mostly front-loaded on the prepare/complete handshake, and the polling pointer sits at the end appropriately. It is, however, fully duplicated in Chinese and English, roughly doubling length without adding information, and the opening 'default host mode' framing delays the actual purpose statement.

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

Completeness4/5

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

For a complex tool with a three-branch oneOf schema and 8 parameters, the description covers the two-phase flow, the token handshake, the legacy escape hatch, and the follow-up polling step well; an output schema exists so return values need not be explained. The gaps are the profile_id instruction that has no matching schema property and the unexplained request_id/job_id, which are the kinds of details an agent needs to construct a valid payload.

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 0%, so the description carries the full burden, and it does explain action values, response being 'full JSON text', preparation_sha256 as the prepare-issued 64-hex token that complete must echo, and confirm_model_call as the legacy-mode gate. However, it never explains job_id provenance (prepare is said to return only instructions_artifact and preparation_sha256), request_id, or project_id/revision semantics, and it instructs the agent to 'use profile_id host' even though profile_id is not a schema property and additionalProperties is false — a mismatch that could cause a rejected call.

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

Purpose4/5

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

The description conveys a specific two-action operation: prepare freezes project/revision and returns instructions, complete submits the LLM-produced JSON for native Core validation and saving. The core purpose ('submit an analysis for a frozen revision') is identifiable but is buried under workflow mechanics and a headline about 'default host mode' rather than a single crisp verb+resource statement. Siblings are only partially distinguished (bx_job_get for polling).

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?

Gives an explicit ordered workflow (prepare → read ALL instruction pages → analyze → complete → poll bx_job_get → read result_revision) and a clear conditional mode: legacy API mode only with confirm_model_call:true plus an explicit API profile. It states when not to expect an extra model API call, which is useful guidance. It does not, however, contrast this tool against nearby siblings like bx_workbench_open or bx_task_validate, so an agent must infer which entry point starts an analysis.

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