Skip to main content
Glama

draft_report_summary

Build a bounded executive summary prompt from computed KPIs and verify cited figures against KPI data, flagging unverified numbers before report use.

Instructions

Build bounded executive summary prompt and verify cited KPI figures.

Args: computed_kpis: ComputeProcessKpisResult dict (or JSON string). audience: Target reader profile ("operations", "contract_admin", "external_client"). cadence: Reporting cadence ("daily", "weekly", "monthly"). candidate_narrative: Optional LLM-drafted prose to verify against KPI numbers. language: Prompt language ("es" or "en"). allowed_extra_numbers: Explicit whitelist for non-KPI reference figures (e.g. years).

Returns: Dict with bounded prompt bundle, verification flag, and any unverified numeric tokens.

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": {
      "computed_kpis": "<computed_kpis>"
    },
    "name": "draft_report_summary"
  }
}

Input Schema

NameRequiredDescriptionDefault
cadenceNodaily
audienceNooperations
languageNoes
computed_kpisYes
candidate_narrativeNo
allowed_extra_numbersNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.25.1

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the return shape: a prompt bundle, a verification flag, and any unverified numeric tokens. It does not say what 'bounded' actually constrains, whether verification failures are surfaced as errors or just extra fields, or whether any external LLM call is made.

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 core action is front-loaded in one sentence and the Args/Returns structure is scannable with no filler prose. Minor waste comes from restating enum options and defaults already present in the schema.

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?

An output schema exists, so the Returns summary is a bonus rather than a necessity, and all six parameters are documented. What is missing for a verification-oriented tool is any statement of what happens on unverified numbers and how it relates to the surrounding KPI-report toolchain.

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 description coverage is 0%, so the Args block does the work, and it covers all six parameters with meaning beyond the bare titles — notably that computed_kpis accepts a dict or JSON string, and that allowed_extra_numbers is a whitelist for non-KPI figures such as years. It partly repeats the enum values already visible in the schema rather than explaining their behavioral effect.

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?

The first sentence names a specific compound action: build a bounded executive-summary prompt and verify cited KPI figures. That clearly distinguishes it from siblings like compute_process_kpis or check_report_data_consistency, though the vague term 'bounded' is never unpacked.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this versus alternatives, no prerequisite (e.g. that computed_kpis must come from compute_process_kpis), and no guidance on when candidate_narrative should be supplied versus omitted. Usage can only be inferred from the parameter list.

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