Skip to main content
Glama

BusCalc — Business & Trade Calculations

Project completion probability (PERT)

buscalc_project_completion_probability_pert
Read-onlyIdempotent

Find the expected finish, the critical path and the chance of meeting a deadline from three-point task estimates. Use this tested BusCalc worksheet when the task matches its inputs and scope. Returns named results, units, formula, assumptions, method version and a source-page URL. No prices or omitted costs are looked up; no private projects or purchases are accessed. Put tool fields inside inputs. Supply units or modelVersion only when listed in inputSchema. Follow its required fields and exact choices. Do not pass the REST calculator field inside MCP arguments.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "inputs": {
        "seed": 7,
        "tasks": [
          {
            "m": 5,
            "o": 3,
            "p": 9,
            "after": "none",
            "label": "Scope and design"
          },
          {
            "m": 12,
            "o": 8,
            "p": 20,
            "after": "1",
            "label": "Build core"
          },
          {
            "m": 8,
            "o": 5,
            "p": 15,
            "after": "1",
            "label": "Build integrations"
          },
          {
            "m": 5,
            "o": 3,
            "p": 10,
            "after": "2, 3",
            "label": "Testing"
          },
          {
            "m": 7,
            "o": 5,
            "p": 14,
            "after": "4",
            "label": "Pilot with customers"
          },
          {
            "m": 3,
            "o": 2,
            "p": 6,
            "after": "2",
            "label": "Launch prep"
          }
        ],
        "trials": 4000,
        "deadline": 36
      }
    },
    "name": "buscalc_project_completion_probability_pert"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitsNo
inputsYes
modelVersionNoOptional expected method version; a mismatch is rejected.

Output Schema

NameRequiredDescriptionDefault
unitsNo
inputsYes
receiptYes
resultsYes
sourceURLYes
calculatorYes
modelVersionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds meaningful context beyond that: it enumerates the returned artifacts (named results, units, formula, assumptions, method version, source-page URL) and states the scope limits (no price or omitted-cost lookups, no private projects or purchases accessed). Minor gap: it does not mention rejection behavior for invalid inputs, which only appears in the schema for modelVersion.

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 correctly, leading with what is computed before the boilerplate. Several sentences are padding or near-tautological ('Use this tested BusCalc worksheet when the task matches its inputs and scope', plus the negative-scope sentence), but each remaining sentence carries at least some operational content and none are confusing.

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?

For a tool with a nested task-array input, optional top-level wrappers, and a declared output schema, the definition covers what the agent needs: what it computes, that results include units/assumptions/formula/method version, and how to nest the arguments. Return-value details are rightly deferred to the output schema; only the argument-ordering semantics of `after` remain unexplained.

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 coverage is low (33%), but the description compensates partially by clarifying the wrapper contract: all tool fields go inside `inputs`, and `units`/`modelVersion` should be supplied only when the schema lists them. It adds nothing about the semantically tricky fields — `after` row references, `trials` range, `deadline` units — which are left to the schema. Net effect is useful structural guidance without real semantic enrichment.

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 opening sentence names a specific verb and concrete outputs: expected finish, critical path, and probability of meeting a deadline, computed from three-point task estimates. An agent can tell it is a PERT/schedule-risk calculator, though the definition never names or contrasts any sibling (e.g., buscalc_probability or the launch simulator), so the differentiation stops at the resource level.

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

Usage Guidelines3/5

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

Usage is only implied by the input shape: it applies to projects described as tasks with optimistic/most-likely/pessimistic estimates and a deadline. The sentence 'Use this tested BusCalc worksheet when the task matches its inputs and scope' is circular and gives no when-not or alternative-tool guidance. The remaining guidance ('Put tool fields inside inputs', 'Do not pass the REST calculator field inside MCP arguments') is invocation hygiene, not tool selection.

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