Skip to main content
Glama

flipper_kb_save

Destructive

Save non-obvious task learnings—gotchas, working sequences, device quirks, and dead ends—to a topic-keyed knowledge file, appending timestamped entries or replacing the topic for future reuse.

Instructions

Record a learning for future tasks, under the repo's knowledge/ folder, keyed by topic. append=True adds a timestamped entry to the topic; append=False replaces it. Save what was NON-OBVIOUS: gotchas, the working sequence, device quirks, dead-ends - so similar future tasks reuse it instead of rediscovering. Do this at the end of any task that taught you something.

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": {
      "topic": "<topic>",
      "content": "<content>"
    },
    "name": "flipper_kb_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicYes
appendNo
contentYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description earns credit by specifying exactly what destruction means (append=False replaces the topic entry) and where the data lands (the repo's knowledge/ folder). It does not mention whether the folder is created if absent or what the write returns, but the output schema covers the latter.

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?

Four sentences, front-loaded with the action and destination, then the append semantics, then the content filter, then the trigger. Dense and free of filler, though the dashes list and the final imperative slightly overlap the earlier guidance.

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?

Adequate for a 3-parameter write tool: the mutation semantics, destination and content policy are all stated, and an output schema exists so return values need no explanation. What remains unexplained is topic key normalization and whether re-saving an existing topic with append=true is safe to rely on.

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 0%, so the description must carry the parameters and it largely does: topic is the lookup key, append toggles timestamped addition vs replacement, and the content guidance effectively defines what belongs in 'content'. The weak spot is topic format or naming constraints, which are left entirely implicit.

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?

Names a specific verb (record a learning) plus the resource and storage location (knowledge/ folder, keyed by topic). It reads as a write operation, which distinguishes it cleanly from the read-oriented flipper_kb_read, flipper_kb_list and flipper_kb_search siblings.

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 explicit timing ("at the end of any task that taught you something") and content criteria (gotchas, the working sequence, device quirks, dead-ends), plus a strong exclusion in spirit: save only what was NON-OBVIOUS. It does not name alternatives or say what to do when a topic already exists, which keeps it below a 5.

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