Skip to main content
Glama
logly

mureo

by logly
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

mureo_state_report_set

Persist structured analysis report summaries to STATE.json for dashboard rendering without re-running the agent. Pass report kind and summary with totals, flags, and narrative.

Instructions

Atomically persist a structured analysis report summary into STATE.json's reports section so the read-only configure dashboard can render the latest report without re-running the agent. report selects the kind — one per skill, listed below; summary carries generated_at (ISO 8601), period, totals (headline figures), flags (one entry per finding) and narrative (the judgement and the proposal). Each part is rendered as what it is — figures as figures, flags as chips, narrative as prose — so a summary that folds all of it into the narrative renders as one unreadable paragraph, and the narrative bound below is enforced. Other report kinds are preserved. Best-effort: a skill should skip this silently where the context MCP is unavailable. Returns the updated state document.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNoOptional path to the file. Defaults to STRATEGY.md / STATE.json in the MCP server's current working directory. Paths outside cwd are refused.
reasonNoWhy this change is being made: one or two sentences naming the evidence and the expected effect. Stored in the journal and on the action_log entry this call produces, for the operator and the next session.
reportYesReport kind: ``daily`` (daily-check), ``weekly`` (weekly-report), ``monthly`` (monthly-report), ``goal`` (goal-review), ``audience`` (audience-review), ``experiment`` (experiment), ``fatigue`` (ad-fatigue-check), ``pacing`` (budget-pacing), ``tracking`` (tracking-health).
summaryYesWrite the structure, not one paragraph. Headline figures go in ``totals`` (spend, conversions, cpa, ctr, clicks, impressions) as raw numbers — 773957, not "¥773,957"; 0.0466, not "4.66%". Each finding goes in ``flags`` as its own entry, with the detail in its ``params``. ``narrative`` keeps only the judgement and the proposal, at most 400 characters: a longer one is refused, never truncated, because a sentence cut in half is worse than a long one. Fields: generated_at (ISO 8601), period, totals (the headline figures above), kpis (the OPTIONAL per-platform split — the breakdown, not the headline row), flags, narrative. Each flag is either a legacy snake_case string OR a structured object {code, severity, params}: code is a canonical vocabulary key (e.g. goals_met, invalid_traffic_suspected, budget_drift, zero_cv_adspots, spend_spike, anomaly_baseline_insufficient), severity is action|watch|info|positive (defaulted from code if omitted), and params holds the detail (adspot ids, yen, ctr) — keep detail in params, NOT in the code and NOT in the narrative. For a finding outside the vocabulary use {code:'custom', severity, label} where label is a string or {locale: text} map. Unknown non-custom codes are rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.20.0
    • addedInput schema / properties / reason
      Added value: +{
+  "description": "Why this change is being made: one or two sentences naming the evidence and the expected effect. Stored in the journal and on the action_log entry this call produces, for the operator and the next session.",
+  "maxLength": 500,
+  "type": "string"
+}
  2. Changed3 schema fields changedv0.13.1
    • changedInput schema / properties / report / description
      Previous value: -"Report kind: ``daily`` (daily-check), ``weekly`` (weekly-report), or ``goal`` (goal-review)."New value: +"Report kind: ``daily`` (daily-check), ``weekly`` (weekly-report), ``monthly`` (monthly-report), ``goal`` (goal-review), ``audience`` (audience-review), ``experiment`` (experiment), ``fatigue`` (ad-fatigue-check), ``pacing`` (budget-pacing), ``tracking`` (tracking-health)."
    • changedInput schema / properties / report / enum
      Previous value: -[
-  "daily",
-  "weekly",
-  "goal"
-]New value: +[
+  "daily",
+  "weekly",
+  "monthly",
+  "goal",
+  "audience",
+  "experiment",
+  "fatigue",
+  "pacing",
+  "tracking"
+]
    • changedInput schema / properties / summary / description
      Previous value: -"Free-form summary object. Convention: generated_at (ISO 8601), period, kpis (per-platform / totals headline numbers), flags, narrative (short text). Each flag is either a legacy snake_case string OR a structured object {code, severity, params}: code is a canonical vocabulary key (e.g. goals_met, invalid_traffic_suspected, budget_drift, zero_cv_adspots, spend_spike, anomaly_baseline_insufficient), severity is action|watch|info|positive (defaulted from code if omitted), and params holds the detail (adspot ids, yen, ctr) — keep detail in params / narrative, NOT in the code. For a finding outside the vocabulary use {code:'custom', severity, label} where label is a string or {locale: text} map. Unknown non-custom codes are rejected."New value: +"Write the structure, not one paragraph. Headline figures go in ``totals`` (spend, conversions, cpa, ctr, clicks, impressions) as raw numbers — 773957, not \"¥773,957\"; 0.0466, not \"4.66%\". Each finding goes in ``flags`` as its own entry, with the detail in its ``params``. ``narrative`` keeps only the judgement and the proposal, at most 400 characters: a longer one is refused, never truncated, because a sentence cut in half is worse than a long one. Fields: generated_at (ISO 8601), period, totals (the headline figures above), kpis (the OPTIONAL per-platform split — the breakdown, not the headline row), flags, narrative. Each flag is either a legacy snake_case string OR a structured object {code, severity, params}: code is a canonical vocabulary key (e.g. goals_met, invalid_traffic_suspected, budget_drift, zero_cv_adspots, spend_spike, anomaly_baseline_insufficient), severity is action|watch|info|positive (defaulted from code if omitted), and params holds the detail (adspot ids, yen, ctr) — keep detail in params, NOT in the code and NOT in the narrative. For a finding outside the vocabulary use {code:'custom', severity, label} where label is a string or {locale: text} map. Unknown non-custom codes are rejected."
  3. Changed1 schema field changedv0.10.37
    • addedInput schema / additionalProperties
      Added value: +false
  4. Changed1 schema field changedv0.10.27
    • changedInput schema / properties / summary / description
      Previous value: -"Free-form summary object. Convention: generated_at (ISO 8601), period, kpis (per-platform / totals headline numbers), flags (list of notable items), narrative (short text)."New value: +"Free-form summary object. Convention: generated_at (ISO 8601), period, kpis (per-platform / totals headline numbers), flags, narrative (short text). Each flag is either a legacy snake_case string OR a structured object {code, severity, params}: code is a canonical vocabulary key (e.g. goals_met, invalid_traffic_suspected, budget_drift, zero_cv_adspots, spend_spike, anomaly_baseline_insufficient), severity is action|watch|info|positive (defaulted from code if omitted), and params holds the detail (adspot ids, yen, ctr) — keep detail in params / narrative, NOT in the code. For a finding outside the vocabulary use {code:'custom', severity, label} where label is a string or {locale: text} map. Unknown non-custom codes are rejected."
  5. Addedv0.10.7

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations provided, the description carries the full disclosure burden—and largely meets it. It discloses atomicity, preservation of other report kinds, enforced narrative length with refusal rather than truncation, validation of unknown codes, best-effort silent skipping, and the return value. It does not discuss overwrite semantics for the same report kind explicitly, though 'one per skill' and 'latest report' imply it.

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 description is dense and front-loaded, beginning with the core purpose before detailing constraints. It is long, but the nested summary payload and lack of an output schema justify most of the length. There is minor overlap between the prose summary-field list and the schema's summary description, but no sentence is purely filler.

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 4-parameter nested write with full schema coverage and no output schema, the description is complete. It states the return value, covers validation and rejection behavior, clarifies preservation semantics, and handles the degraded-context case. An agent has enough information to invoke the tool correctly and interpret the outcome.

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

Parameters5/5

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

Schema coverage is 100%, yet the description adds substantial meaning beyond the schema: it decodes each report enum value, prescribes raw-number formatting with concrete examples, defines the flag object shape including severity and custom-code fallback, and explains rejection behavior. This transforms the schema from a type declaration into an actionable contract.

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?

The description opens with 'Atomically persist a structured analysis report summary into STATE.json's reports section,' naming a precise verb, resource, and purpose. It clearly targets the reports section and the configure dashboard rendering need, distinguishing it from the other mureo_state_* setters without ambiguity.

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 clear context: reports are one per skill, used so the dashboard can render the latest report without re-running the agent, and other report kinds are preserved. It also provides an explicit when-not condition: 'a skill should skip this silently where the context MCP is unavailable.' It does not name a specific sibling alternative, so it stops short of the highest bar.

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

Deploy Server

Other Tools