apex-memory

brief

Loads domain-specific start-of-task context—identity, open issues, index, decisions by status, open status items, and recent log entries—so agents can begin work informed.

Instructions

Start-of-task read: store identity and open check problems, the index, decisions by status and open status items, then the last log_entries log entries. max_chars caps the index and the status block separately; the log entries always appear in full.

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": {
      "domain": "<domain>"
    },
    "name": "brief"
  }
}

Input Schema

Name	Required	Description	Default
`domain`	Yes
`max_chars`	No
`log_entries`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Nov 3, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It does add genuinely useful behavior: max_chars caps the index and status block separately while log entries always appear in full, which prevents wrong assumptions about truncation. However, it says nothing about read-only semantics, permissions, or what happens when the domain is missing or empty.

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 dense sentences, front-loaded with the return contents and then the truncation semantics. Every clause carries information, though the enumerated return list is somewhat run-on and could be structured more cleanly.

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 multi-source aggregation read with no output schema and no annotations, the description covers the return shape and truncation rules well. It leaves the required domain parameter and any error/empty-store behavior unexplained, so it is adequate but not complete.

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 coverage is 0%, so the description must compensate. It does explain max_chars (separate caps on index and status block) and log_entries (last N entries, always in full), which adds real meaning beyond bare defaults. The required 'domain' parameter is never explained, leaving a significant gap.

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 names a specific verb ('Start-of-task read') and enumerates the exact resources returned: identity, open check problems, the index, decisions by status, open status items, and recent log entries. This lets an agent distinguish it from single-resource siblings like read, log_query, or check. It stops short of explicitly naming which sibling it replaces for a full context load.

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?

'Start-of-task read' implies the usage context (kickoff of a task) but gives no explicit when-not conditions and does not name alternatives such as read or log_query for partial lookups. The agent must infer that this is the broad context-priming call versus targeted reads.

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

Deploy Server