eng-leadership-toolkit

Engineering leadership benchmarks & mentoring statistics

get_engineering_leadership_benchmarks

Read-onlyIdempotent

Real benchmarks from 3,662 paid 1:1 mentoring sessions with 300+ engineering leaders since 2019: mentee seniority mix, most-demanded leadership topics of 2025, time-to-results, team-health delivery thresholds (sprint completion, roadmap %, manager time per report), and practice outcome stats (NPS, referral rate). First-party data, CC BY 4.0 — citable.

Input Schema

Name	Required	Description	Default
`topic`	No	Which benchmark set to return (default: all) One of: practice-stats, mentee-mix, topic-demand, team-health-thresholds, all.
`context`	No	Optional. A short description of your goal and why you are calling this tool. Recorded as intent so the tools can be improved; it never changes the answer.

Output Schema

Name	Required	Description
`math`	No	Napkin math behind the case.
`email`	No	Forwardable email to the manager.
`level`	No	Seniority level the score maps to, when the tool computes one.
`report`	Yes	The full human-readable report.
`source`	Yes	Canonical marian.coach page this answer is derived from.
`verdict`	No	Headline verdict, when the tool returns one.
`evidence`	No	Sources the case may cite.
`onePager`	No	Manager-facing one-pager, forwardable to finance.
`salaryEur`	No	Estimated 2026 Western-Europe gross annual salary in EUR.
`objections`	No	The usual objections, answered.
`slackShort`	No	Slack/Teams-length version of the ask.
`totalScore`	No	Weighted 0-10 score, when the tool computes one.
`valueFormula`	No	The four value lines to add up (money saved, cost of delay, missed opportunity, roadmap slippage) plus the count-then-halve CFO rule.
`talkingPoints`	No	Five talking points for the conversation.
`workedExamples`	No	Three published worked examples: EM, Director, Staff Engineer.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 11, 2026

changedInput schema / properties / context / description

Previous value: -"Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""New value: +"Optional. A short description of your goal and why you are calling this tool. Recorded as intent so the tools can be improved; it never changes the answer."

changedInput schema / properties / topic / description

Previous value: -"Which benchmark set to return (default: all)"New value: +"Which benchmark set to return (default: all) One of: practice-stats, mentee-mix, topic-demand, team-health-thresholds, all."

removedInput schema / properties / topic / enum

Removed value: -[
-  "practice-stats",
-  "mentee-mix",
-  "topic-demand",
-  "team-health-thresholds",
-  "all"
-]

removedInput schema / required
```
Removed value: -[
-  "context"
-]
```

Changed2 schema fields changedAug 27, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
+  "type": "string"
+}

addedInput schema / required
```
Added value: +[
+  "context"
+]
```

Changed9 schema fields changedAug 17, 2026

addedOutput schema / properties / email

Added value: +{
+  "additionalProperties": false,
+  "description": "Forwardable email to the manager.",
+  "properties": {
+    "body": {
+      "type": "string"
+    },
+    "subject": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "subject",
+    "body"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / evidence

Added value: +{
+  "description": "Sources the case may cite.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "claim": {
+        "type": "string"
+      },
+      "source": {
+        "type": "string"
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "claim",
+      "source",
+      "url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / math

Added value: +{
+  "additionalProperties": false,
+  "description": "Napkin math behind the case.",
+  "properties": {
+    "askEur": {
+      "type": "number"
+    },
+    "discountedEur": {
+      "type": "number"
+    },
+    "lines": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "note": {
+      "type": "string"
+    },
+    "packPriceEur": {
+      "type": "number"
+    },
+    "roiMultiple": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "totalEur": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "lines",
+    "totalEur",
+    "discountedEur",
+    "askEur",
+    "packPriceEur",
+    "roiMultiple",
+    "note"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / objections

Added value: +{
+  "description": "The usual objections, answered.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "answer": {
+        "type": "string"
+      },
+      "objection": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "objection",
+      "answer"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / onePager

Added value: +{
+  "additionalProperties": false,
+  "description": "Manager-facing one-pager, forwardable to finance.",
+  "properties": {
+    "sections": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "body": {
+            "type": "string"
+          },
+          "bullets": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "heading": {
+            "type": "string"
+          },
+          "table": {
+            "items": {
+              "items": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "string"
+                }
+              ],
+              "type": "array"
+            },
+            "type": "array"
+          }
+        },
+        "required": [
+          "heading"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "title": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "title",
+    "sections"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / slackShort

Added value: +{
+  "description": "Slack/Teams-length version of the ask.",
+  "type": "string"
+}

addedOutput schema / properties / talkingPoints

Added value: +{
+  "description": "Five talking points for the conversation.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / valueFormula

Added value: +{
+  "additionalProperties": false,
+  "description": "The four value lines to add up (money saved, cost of delay, missed opportunity, roadmap slippage) plus the count-then-halve CFO rule.",
+  "properties": {
+    "heading": {
+      "type": "string"
+    },
+    "lines": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "rule": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "heading",
+    "lines",
+    "rule"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / workedExamples

Added value: +{
+  "description": "Three published worked examples: EM, Director, Staff Engineer.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "kpis": {
+        "type": "string"
+      },
+      "math": {
+        "type": "string"
+      },
+      "role": {
+        "type": "string"
+      },
+      "setup": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "role",
+      "setup",
+      "kpis",
+      "math"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed1 schema field changedJul 26, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "level": {
+      "description": "Seniority level the score maps to, when the tool computes one.",
+      "type": "string"
+    },
+    "report": {
+      "description": "The full human-readable report.",
+      "type": "string"
+    },
+    "salaryEur": {
+      "description": "Estimated 2026 Western-Europe gross annual salary in EUR.",
+      "type": "number"
+    },
+    "source": {
+      "description": "Canonical marian.coach page this answer is derived from.",
+      "type": "string"
+    },
+    "totalScore": {
+      "description": "Weighted 0-10 score, when the tool computes one.",
+      "maximum": 10,
+      "minimum": 0,
+      "type": "number"
+    },
+    "verdict": {
+      "description": "Headline verdict, when the tool returns one.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "report",
+    "source"
+  ],
+  "type": "object"
+}

First observedJul 12, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already establish the safe read-only, idempotent, non-destructive profile, so the description correctly focuses on other context: the data is first-party, sourced from 3,662 sessions with 300+ leaders since 2019, and licensed CC BY 4.0 for citation. It does not discuss recency guarantees or whether the underlying dataset updates, which is the only meaningful remaining gap for a static dataset.

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?

One dense sentence followed by a short provenance/licensing tagline. It is front-loaded with what is returned, though the enumeration is packed tightly enough that the individual datasets are easy to skim past.

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?

With an output schema present and 100% parameter coverage, the description only needs to justify existence and trust, which the sample size, source, and license do well. The one shortfall is that it never tells an agent when this tool is the right choice over its advisory siblings.

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 the baseline is 3. The description's list of benchmark sets (mentee mix, topic demand, team-health thresholds, practice stats) loosely mirrors the 'topic' parameter's allowed values, adding mild reinforcement but no format or default details beyond the schema.

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 description names the specific resource (first-party benchmarks from 3,662 paid mentoring sessions) and enumerates the concrete datasets returned: mentee seniority mix, topic demand, time-to-results, team-health thresholds, practice outcome stats. An agent can tell this is a data-retrieval tool versus the advisory siblings, though it never explicitly contrasts itself with them.

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 use this versus alternatives such as build_mentoring_business_case or get_one_on_one_playbook. 'Citable' hints that it is for citation in documents, but this is inference rather than guidance, and no exclusions or prerequisites are given.

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

All eng-leadership-toolkit tools Inspect

Try in Browser

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.