Skip to main content
Glama

Dayze — Life Context

Create Goal

create_goal

Create a life goal the user explicitly wants to track. Not a calendar event or streak tracker. Numeric goals are totals that build up and need target_value and target_unit; rate goals are a number per calendar month that can go down, such as monthly revenue, and need the same two fields; habit goals need habit_frequency and habit_target_count. Ask for missing facts; never invent aspirations. ($0.10; API key required)

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": {
      "title": "<title>"
    },
    "name": "create_goal"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYesGoal title, e.g. Run a half marathon.
categoryNoGoal category, e.g. health.
priorityNoPriority level: high, medium or low, e.g. medium.
obstaclesNoWhat might get in the way, e.g. Long work travel.
motivationNoWhy the goal matters to the user, e.g. To stay healthy for my kids.
request_idNoClient idempotency key (retries return original result).
start_dateNoStart date YYYY-MM-DD, e.g. 2026-10-17.
descriptionNoWhat the goal is, e.g. Run a half marathon by March.
target_dateNoTarget date YYYY-MM-DD, e.g. 2026-12-31.
target_typeNoGoal type: completion, numeric, rate or habit, e.g. numeric.
target_unitNoUnit for target_value, e.g. km.
target_valueNoNumber the goal aims for, e.g. 21.
current_valueNoProgress so far in target_unit, e.g. 5.
habit_frequencyNoHow often the habit repeats, e.g. weekly.
idempotency_keyNoAlias for request_id.
checkin_frequencyNoHow often to check in on the goal: daily, weekly or monthly, e.g. weekly.
habit_target_countNoTimes per period needed to hit the habit target, e.g. 3.

Output Schema

NameRequiredDescriptionDefault
goalYes
accountNoThe Dayze account this data belongs to. With more than one Dayze connection, name it in the answer.
goal_idYes
messageYes
verifiedNo
provenanceNoWhich connector wrote the record and which connected Dayze account received it.
inspect_urlNoThe Dayze page that shows the saved record.
inspect_noteNoWhat inspect_url opens. Never quote the record id.
progress_loggedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changed
    • addedInput schema / properties / category / description
      Added value: +"Goal category, e.g. health."
    • addedInput schema / properties / checkin_frequency / description
      Added value: +"How often to check in on the goal: daily, weekly or monthly, e.g. weekly."
    • addedInput schema / properties / current_value / description
      Added value: +"Progress so far in target_unit, e.g. 5."
    • addedInput schema / properties / description / description
      Added value: +"What the goal is, e.g. Run a half marathon by March."
    • addedInput schema / properties / habit_frequency / description
      Added value: +"How often the habit repeats, e.g. weekly."
    • addedInput schema / properties / habit_target_count / description
      Added value: +"Times per period needed to hit the habit target, e.g. 3."
    • addedInput schema / properties / motivation / description
      Added value: +"Why the goal matters to the user, e.g. To stay healthy for my kids."
    • addedInput schema / properties / obstacles / description
      Added value: +"What might get in the way, e.g. Long work travel."
    • addedInput schema / properties / priority / description
      Added value: +"Priority level: high, medium or low, e.g. medium."
    • addedInput schema / properties / start_date / description
      Added value: +"Start date YYYY-MM-DD, e.g. 2026-10-17."
    • addedInput schema / properties / target_date / description
      Added value: +"Target date YYYY-MM-DD, e.g. 2026-12-31."
    • addedInput schema / properties / target_type / description
      Added value: +"Goal type: completion, numeric, rate or habit, e.g. numeric."
    • addedInput schema / properties / target_unit / description
      Added value: +"Unit for target_value, e.g. km."
    • addedInput schema / properties / target_value / description
      Added value: +"Number the goal aims for, e.g. 21."
    • addedInput schema / properties / title / description
      Added value: +"Goal title, e.g. Run a half marathon."
  2. Changed1 schema field changed
    • changedInput schema / properties / target_type / enum
      Previous value: -[
      -  "completion",
      -  "numeric",
      -  "habit"
      -]New value: +[
      +  "completion",
      +  "numeric",
      +  "rate",
      +  "habit"
      +]
  3. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only but non-destructive, non-open-world write, so the safety profile is covered. The description adds genuinely new behavioral context: a per-call cost of $0.10, an API-key requirement, and the anti-fabrication rule about asking for missing facts. It does not say what happens on duplicate submission beyond what the schema's idempotency fields imply, 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?

The scope constraint is front-loaded in the first sentence, followed by type routing and then the behavioral rule, which is a sensible order for an agent scanning quickly. The middle clause is dense and semicolon-chained, and the trailing "($0.10; API key required)" is useful but tacked on rather than integrated.

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 a 17-parameter creation tool with full schema descriptions, an output schema, and annotations, the description covers the parts structured data cannot: scope, type-specific field requirements, cost/auth, and the no-fabrication rule. Remaining details like priority, motivation, and checkin_frequency are adequately documented in the schema, so nothing an agent needs to call this correctly is missing.

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 the baseline is 3, but the description earns a bump by documenting cross-field dependencies the schema cannot express: numeric and rate goals both require target_value and target_unit, and habit goals require habit_frequency and habit_target_count. That conditional logic is the highest-value thing an agent needs before calling, and it is stated explicitly.

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?

"Create a life goal the user explicitly wants to track" states a specific verb and resource, and the follow-up "Not a calendar event or streak tracker" actively separates it from adjacent concepts. The enumeration of numeric, rate, and habit goal types further pins down what gets created.

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?

The description gives a clear when-to-use condition (the user explicitly wants to track it) and a when-not (not a calendar event or streak tracker), plus an instruction to ask for missing facts rather than invent aspirations. It stops short of naming an actual sibling tool such as update_goal or create_tracker as the alternative path, so routing to concrete siblings is left to inference.

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.