Skip to main content
Glama

release_gate

Decides whether a chapter batch can be released by applying a compliance veto and anchor-based scoring, returning release, revise, or block.

Instructions

【质检层·第二层】发布闸门(每 30 章一批 + 首发):合规一票否决(不计分)+ 锚点制百分制评分(只报命中档,不报感觉分)。≥80 且无致命 → 放行;70-79 → 修改后发布;<70 或致命 → 禁止发布。 四档评分:A 满分 / B 轻微扣 / C 明显扣 / D 严重扣;命中多档取最低档。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "compliance_passed": "<compliance_passed>",
      "scores": "<scores>"
    },
    "name": "release_gate"
  }
}

Input Schema

NameRequiredDescriptionDefault
scoresYes
project_idYes项目 ID(内部代号,如“默者”)
fatal_issuesNo致命项清单(合规/崩人设等)
存稿章数No
compliance_passedYes合规终审(COMPLIANCE_ITEMS 全项通过)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden. It does disclose genuinely behavioral content the schema cannot: the compliance one-vote veto is excluded from scoring, and the tool reports only the tier actually hit rather than a subjective numeric score. What is missing is whether calling it records/persists a release decision or mutates project state, and what the response looks like for the 'forbidden to publish' branch.

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?

Two compact sentences plus a short grading key, front-loaded with the layer label and the decision thresholds. The bracket tag '【质检层·第二层】' and the aside '不报感觉分' are slightly decorative but do convey positioning and a reporting property. Nothing is redundant with the schema.

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

Completeness3/5

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

For a 5-parameter tool with a nested required object, no annotations and no output schema, the description covers the decision logic well, which effectively substitutes for a return-value spec. It does not cover the undocumented chapter-count parameter or how the 30-chapter batch scope is determined, and says nothing about persistence or side effects of a gate decision.

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?

With schema coverage at 60%, the description adds real meaning beyond the schema: it explains that 'compliance_passed' acts as a veto independent of the score, that fatal items override the threshold, and that when multiple deduction tiers apply the lowest tier wins. That last rule is a genuine semantic the enum schema does not express. It still leaves the grade-to-100-point mapping unstated (critical given the ≥80 cutoff) and never mentions the undocumented '存稿章数' parameter.

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 states a specific function: a release gate that combines a compliance veto with an anchor-based 100-point score over four graded dimensions, and it spells out the three decision outcomes. An agent can see it is a final publish/no-publish arbitration rather than a per-chapter quality check. It does not name any sibling (e.g. review_chapter, check_redline) as the narrower alternative, so differentiation must be inferred from the batch cadence.

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

Usage Guidelines3/5

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

The cadence '每 30 章一批 + 首发' implies when the gate is invoked (at batch boundaries and at series launch), and the thresholds define what happens with the result. However, there is no explicit when-not guidance and no named alternative for single-chapter or ad-hoc checks, so routing between this and review_chapter/check_* siblings is left to inference.

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