Skip to main content
Glama

memory_bootstrap

Read-only

Load a project memory briefing with cross-project user memory, pinned decisions, facts, preferences, procedures, and recent updates. Skip if HiveMem already injected one; use only for other projects.

Instructions

获取项目记忆简报:用户级记忆(跨项目)优先加载,然后置顶记忆、关键决策、关键事实/偏好/流程、最近更新索引与本设备/本工具记忆索引。上下文里已有以「## HiveMem 项目简报(自动注入」开头的段落时不要调用——宿主插件已经注入过,再调只会得到第二份;只在没有注入(宿主未装插件)或需要别的项目时用。简报是策展视图,可能被截断(truncated=true,末尾附总数与索引指针),全量用 memory_index。HTTP 模式下 project 必填;传新项目名会自动创建该项目(响应含 created 标记)。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "memory_bootstrap"
  }
}

Input Schema

NameRequiredDescriptionDefault
budgetNo简报字符预算(512..8000,默认 2600);宿主 prompt 紧张时调小,需要更多上下文时调大
projectNo项目名或 id。省略时从当前工作目录自动解析
task_hintNo当前任务简述(如"修登录超时 bug");提供时简报会优先附上任务相关记忆

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.4

TDQS

A4.6/5.0
Behavior4/5

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

Beyond readOnlyHint=true it discloses truncation behavior (truncated=true with totals and index pointers appended) and that a new project name is auto-created with a `created` marker in the response. The one caveat is that this auto-creation is a state side effect that slightly stretches the readOnlyHint annotation, but the description discloses it openly rather than hiding it, so an agent is not misled. It does not describe ordering or cost beyond the budget cap, which keeps it from 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.

Conciseness4/5

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

Front-loaded with purpose, then the do-not-call warning in bold, then edge cases — a sensible priority order with no filler. It is a single dense run-on paragraph with several clauses stacked by semicolons, which costs a little scannability compared with the content density it carries.

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?

There is no output schema, and the description compensates by explaining the response shape (curated view, possible truncation, totals plus index pointers, `created` flag) and the transport-specific requirement for project. For a three-parameter read tool that is everything needed to call it correctly and interpret what comes back.

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?

Schema coverage is 100%, so baseline is 3, but the description adds operational meaning: project is mandatory under HTTP mode (a constraint absent from the schema), a new project name triggers auto-creation reported via `created`, and budget should be lowered when the host prompt is tight. task_hint's effect (task-relevant memories prioritized) is broadly echoed in the schema, so not every sentence adds new information.

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?

States a specific verb (获取/load) and object (项目记忆简报) and then enumerates the exact sections returned: 用户级记忆、置顶记忆、关键决策、关键事实/偏好/流程、最近更新索引、本设备/本工具记忆索引. It also explicitly contrasts itself with memory_index ('全量用 memory_index'), so an agent can separate the two without opening either schema.

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?

Gives an explicit negative trigger in bold ('上下文里已有以「## HiveMem 项目简报(自动注入」开头的段落时不要调用'), the reason (会得到第二份), and the positive conditions (宿主未装插件, 需要别的项目时). It also names a concrete alternative for the full-corpus case (memory_index), which is exactly the when/when-not/alternative structure the dimension rewards.

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