eng-leadership-toolkit

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

Annotations already mark the operation as read-only and idempotent, and the description adds valuable behavioral detail: two call modes, verdict categories, top-2 gaps with actionable moves, and provenance ('Built from 3,400+ mentoring sessions'). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three well-structured sentences that front-load the core question, then efficiently detail the test dimensions, verdict, gap analysis, and call behavior without fluff. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a single optional parameter and a rich output schema, the description covers purpose, call modes, output structure (verdict + gaps), and credibility. The tool is simple enough that the description is fully complete.

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

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

The input schema already has 100% coverage for the 'answers' parameter, including the omit behavior and answer format. The description adds the important constraint that all 17 answers are needed for the verdict, reinforcing the dual-mode usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool answers 'should I become a team lead?' and describes the 17-question test, six dimensions, verdict options, and gap analysis. It distinguishes itself from sibling tools by focusing specifically on readiness assessment rather than guidance or benchmarks.

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

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

The description provides explicit call instructions ('Call without answers to get the questionnaire; call with all 17 answers to get the verdict') which makes usage clear. It does not explicitly mention alternatives or when not to use, but the context is well-defined.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it's a safe, repeatable operation. The description adds valuable behavioral details beyond that: 'Uses only what you pass in — a missing problem renders as a visible bracket, never an invented one,' which is a strong anti-hallucination guarantee. Also covers language and formality options.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, then efficiently lists deliverables in a comma-separated flow. It's longer than average but every clause adds product detail. The closing 'From 3,400+ mentoring sessions' is credibility rather than function, slightly detracting from conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 16 parameters and a rich output schema, the description covers the main use cases, personalization options, and key behavioral rules. It doesn't explain legacy parameters like avg_salary_eur or delayed_revenue_eur, but the schema already does. The output schema handles return values, so no need to detail them here.

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

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

Schema coverage is 100%, so all 16 parameters have descriptions. The tool description adds contextual meaning by showing how parameters combine (e.g., 'senior people at risk x replacement cost' explains at_risk_attrition and avg_salary_eur) and by explaining the placeholder behavior for 'problem'. It doesn't simply repeat the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Build the case that gets your company to pay for leadership mentoring,' immediately establishing the tool's unique role. It then enumerates concrete outputs (email, one-pager, talking points), clearly distinguishing it from sibling tools that calculate value or estimate costs.

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

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

The title and description give clear context: use this when the goal is to persuade the company to fund mentoring. It doesn't explicitly exclude alternatives, but the personalization and components (e.g., 'email to your manager') make the use case obvious. No explicit when-not-to-use, hence not a 5.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds behavioral context beyond annotations, such as 'Unscored skills default to the level's baseline' and the specifics of the 5-pillar scoring model, which enriches understanding of the calculation behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, with the first packing in key details (what it does, the output) and the second clarifying the default behavior for unscored skills. No fluff or repetition; every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (15 skills, 5 pillars, multiple outputs), the description covers all essential aspects: inputs (level and scores), computation model, outputs, and default behavior. An output schema exists, so return values don't need to be spelled out. The description also adds context about the 2026 Western-Europe salary estimate.

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

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

Schema coverage is 100%, but the description adds semantic meaning beyond the schema by explaining that the level 'sets pillar weights and baseline' and describing the 15 skills across 5 pillars. This gives context for how the score parameters relate to the calculation, adding value beyond the raw parameter descriptors.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Assess a software developer's market value' and details the outputs (weighted score, seniority level, salary estimate). It distinguishes itself from sibling tools like calculate_engineering_manager_value by specifying the target role (software developer) and the unique scoring framework.

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

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

The description provides clear context for when to use the tool (e.g., for developers, with skill scores and a level) but does not explicitly mention alternatives or when not to use it. The sibling tool names imply differentiation, but no direct 'use this instead of X' guidance is present.

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

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

Annotations already declare readOnly, idempotent, and non-destructive; the description adds the scoring structure (15 skills, 5 pillars), weighting by level, output of salary and level, and the default-to-baseline behavior for unscored skills. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with the purpose front-loaded. Each sentence adds value, though the 'Same logic as the live EM salary calculator' sentence is optional provenance rather than essential guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the rich schema, output schema, and annotations, the description is complete: it explains what the tool does, how skills are weighted, what outputs are produced, and the default behavior for omitted skills. Nothing critical is left unexplained.

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

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

The input schema already provides full parameter descriptions, including enum values, valid score keys, and baseline defaults. The description adds pillar groupings but does not materially extend the parameter semantics beyond what the schema already covers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Assess') and defines the resource ('engineering leader's market value'), then enumerates concrete outputs: total score, level, and 2026 salary estimate. This clearly distinguishes it from sibling calculate_developer_value (developers) and other leadership-readiness tools.

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

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

It clearly identifies the target user (engineering leader) and the level-based weighting context, implying it is for EM market-value assessment rather than developer valuation or mentoring. However, it does not explicitly name alternatives or state when not to use this tool.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful behavioral context: it is an advisory tool grounded in 3,400+ sessions, includes a self-test, and covers specific comparison dimensions (time horizon, domain experience). No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core decision purpose, followed by the key content dimensions and an evidence-based credibility note. Every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only advisory tool with an output schema, the description fully covers purpose, content, and target user. The empirical basis ('3,400+ sessions') adds credibility. No important behavioral or contextual gaps remain.

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

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

The single optional parameter 'situation' is fully described in the schema (100% coverage), so the description does not need to add much. The description reinforces that the situation maps to a recommendation via the three-question test, which slightly extends the schema meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Decide whether' and clearly names the resource (mentor, coach, or advisor) and audience (engineering leader). It differentiates from sibling tools like assess_team_lead_readiness or calculate_engineering_manager_value by focusing on the choice between support roles.

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

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

The description makes the use case clear: deciding which type of support an engineering leader needs. It does not explicitly name alternatives or exclusions, but the purpose is distinct enough among siblings that an agent can infer when to invoke it.

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

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

The description adds meaningful context beyond the readOnlyHint annotation by specifying return values (per-session range, program total, red flags) and data sources (ICF Global Coaching Study 2025, Tandem Coach 2026, CEE market surveys). This provides transparency about what the tool produces and the basis for estimates, which is not captured in annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose, followed by output details and data sources. Every sentence earns its place with no redundancy or filler. It is highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 parameters (4 required) with complete schema coverage and an output schema. The description explains the return values (range, total, red flags) and data provenance, and no critical behavioral information is missing. Combined with annotations, it is fully complete for an AI agent to select and invoke correctly.

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

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

The input schema already has 100% parameter descriptions with rich details (e.g., territory rates, client role pricing, scope discounts). The description mentions engagement length and coach territory but doesn't add meaningful new parameter semantics beyond the schema. Baseline 3 is appropriate because the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool estimates fair market rates for coaching/mentoring with specific inputs (coaching type, client role, etc.) and outputs (per-session range, program total, red flags). This distinctly differentiates it from sibling tools like 'assess_team_lead_readiness' or 'calculate_developer_value' which serve different purposes.

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

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

The description implies usage for cost estimation through phrases like 'Fair market rate' and 'Returns a per-session range'. It doesn't explicitly state when not to use it or name alternative tools, but the context is clear given the sibling tools' distinct purposes. No explicit exclusions, but the intended use case is obvious.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds valuable context beyond annotations by specifying data provenance (3,400+ sessions, since 2019), data scope, and licensing (CC BY 4.0, citable), which aids appropriate use and citation. No behavioral warnings are needed given the read-only nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense sentence listing data categories, followed by a short licensing note. It is well-organized and front-loaded, with no redundant filler. The length is appropriate given the richness of information conveyed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only data retrieval tool with an output schema, the description is complete. It provides data provenance, content categories, and citation/licensing info, covering all necessary context for an agent to select and invoke the tool appropriately.

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

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

The schema covers the single 'topic' parameter with an enum and description, achieving 100% coverage, which typically merits a baseline of 3. The description contributes extra meaning by illustrating the type of data each benchmark set contains, helping to infer what the enum values return, though the mapping is not explicit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what the tool does: it returns real benchmarks from mentoring sessions, listing specific data categories (mentee seniority mix, leadership topics, time-to-results, team-health thresholds, practice outcomes). It is distinct from sibling tools by focusing on benchmark data rather than assessment, calculation, or coaching guidance.

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

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

The description does not explicitly mention when to use this tool instead of siblings, but the content listed makes its purpose clear for anyone needing benchmark statistics. No exclusions or alternative tool references are provided, so context is clear but not fully explicit.

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

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

Annotations already declare read-only and non-destructive behavior, so the description adds little beyond confirming the content. The statistic about mentees is informational, not behavioral. No contradictions found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences that efficiently pack a clear statement of purpose and a list of specific deliverables. Every sentence earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-parameter read-only tool with an output schema, the description sufficiently describes the content and audience. It covers what the guidance entails, making it complete for selection and invocation purposes.

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

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

The input schema has zero parameters, so there is nothing to explain. The description is not required to cover parameter semantics, and the baseline of 4 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as providing guidance for the IC→manager transition, listing specific topics like the EM responsibility triangle, failure modes, and self-check questions. This differentiates it from sibling tools such as assess_team_lead_readiness.

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

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

The description implies when to use the tool—anyone in or considering the IC→manager transition—and even mentions readiness self-check questions, but it does not explicitly state when not to use it or name alternatives. The context is clear but excludes no alternatives.

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

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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description doesn't need to repeat these. It adds context about the content (actual templates from 3,400+ sessions) but no additional behavioral details like return format or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose and lists examples efficiently. Every clause earns its place without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter, full schema coverage, and a safety profile provided by annotations, the description fully covers what the tool does and when to use it. An output schema exists, so returns need not be explained.

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

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

Schema coverage is 100% with detailed enum descriptions for the 'situation' parameter. The description briefly lists the same situations in prose but does not add significant meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides situation-specific 1:1 scripts and templates, listing concrete use cases. This distinguishes it from sibling tools that focus on assessments, calculations, or general guidance.

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

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

The description implies when to use the tool by enumerating specific situations (e.g., underperformance, promotion), giving clear context. It does not explicitly exclude alternatives or mention sibling tools, but the listed scenarios make intended usage obvious.

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