Skip to main content
Glama

Save journal entry

save_journal
DestructiveIdempotent

Save the user's journal entry for a day: the evening reflection (win, mistakes, lessons, improve), the morning intention, or answers to their own journal prompts as {id, answer}. Use get_journal to read entries back. Saving a section (morning or evening) again for the same date replaces that section and keeps the other; a morning intention also updates the app's "ONE thing" card. Nothing is added to the schedule. Returns {ok:true, date, type}; ok:false (e.g. empty_answers) saved nothing. Not preview-gated.

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": {
      "type": "<type>"
    },
    "name": "save_journal"
  }
}

Input Schema

NameRequiredDescriptionDefault
winNoEvening: today's biggest win, distilled from their answer
dateNoYYYY-MM-DD in the user's local calendar, e.g. "2026-11-20". Omit for their local today.
typeYes"evening" (reflection: win / mistakes / lessons / improve) or "morning" (intention).
answersNoAnswers to the user's own journal prompts, e.g. [{"id":"gratitude","answer":"my sister's call"}].
improveNoEvening: what to improve tomorrow
lessonsNoEvening: lessons learned
mistakesNoEvening: mistakes/what went sideways (may be "none")
intentionNoMorning: today's intention / top priority

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description reconciles those two by explaining exactly what is overwritten: re-saving a section for the same date replaces that section and keeps the other. It further discloses a side effect ('a morning intention also updates the app's "ONE thing" card'), a no-side-effect guarantee ('Nothing is added to the schedule'), the failure mode (ok:false e.g. empty_answers saved nothing), and that the call is not preview-gated.

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 the write operation and its three variants, then behavioral caveats, then the return shape; no sentence is filler. It is dense with semicolon-chained clauses, which slightly hurts scanability but never wastes words.

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?

For an 8-parameter mutation with no output schema, the description supplies the missing return contract ({ok:true, date, type} plus the ok:false failure case), the destructive replacement semantics, and the cross-tool side effect. An agent has everything needed to call it correctly and interpret the result.

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 description coverage is 100%, so each field is already documented as evening-only or morning-only and date omission defaults to local today. The description restates that grouping and the {id, answer} answers shape but adds no new syntax, constraints, or examples beyond the schema, so the baseline of 3 applies.

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 and resource ('Save the user's journal entry for a day') and then enumerates the three content shapes it accepts: evening reflection fields, morning intention, or prompt answers as {id, answer}. The sibling get_journal is named as the read counterpart, so the write-vs-read split is unambiguous.

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 get_journal to read entries back' routes the agent to the correct sibling for reads, and 'Nothing is added to the schedule' excludes a plausible but wrong interpretation given the task/routine siblings. There is no explicit when-not for journal writes themselves (e.g. when to prefer ask_coach for reflection), so it stops short of a full routing rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources