Skip to main content
Glama

suggest_instruction_updates

Suggests CLAUDE.md or AGENTS.md rules from friction that recurs across sessions, citing past sessions as evidence. Read-only; apply suggested rules with sync_memory.

Instructions

Suggest CLAUDE.md / AGENTS.md rules from friction that recurs across sessions, with the sessions as evidence. Read-only: never writes files (use sync_memory to apply a rule).

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": "suggest_instruction_updates"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNo
sourcesNoall
targetsNo
days_backNo
max_suggestionsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden, and it does deliver the single most important trait: it never writes files and only produces suggestions backed by session evidence. It is silent on cost/latency for a scan over days_back of session history, on how suggestions relate to rules that already exist in the target files, and on any prerequisite for the sources being indexed.

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

Conciseness5/5

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

Two tight sentences, front-loaded with what is produced and from what evidence, followed by the safety/routing clause. No filler and no repetition of the tool name.

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?

The output schema means return values need no explanation, and the read-only posture is covered, but for a five-parameter tool with zero schema coverage the definition leaves the agent guessing about what 'friction', 'sources', and the day window actually mean. Adequate as a one-line pitch, thin as an operating manual.

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

Parameters2/5

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

Schema description coverage is 0% across five parameters, so the description must compensate and it does not — project, sources, days_back, and max_suggestions are never mentioned. Only the targets default (CLAUDE.md / AGENTS.md) is inferable from the prose, leaving the scope and volume controls undocumented.

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?

States a specific verb (suggest) and a concrete resource (CLAUDE.md / AGENTS.md rules) plus the input signal it mines (friction recurring across sessions) and the evidence it attaches. It clearly separates itself from the write path by naming sync_memory, though it does not explicitly distinguish itself from the close sibling suggest_rules.

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?

"use sync_memory to apply a rule" gives an explicit alternative for the follow-up action, and "Read-only: never writes files" tells the agent when this tool is the safe choice. It stops short of saying when *not* to run it (e.g. vs. suggest_rules or find_friction_patterns), so the routing picture is clear but not exhaustive.

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