elc-toolkit

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

Beyond the readOnly/idempotent annotations, the description discloses the tool is checklist-based, specifies the five checklist items (speaker network, promo channels, local operator, realistic targets, promo budget), and describes the conditional output flow (questions vs verdict + gaps). This adds meaningful behavioral context about how the tool behaves across invocations. 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?

Two sentences, front-loaded with the core purpose, and every clause carries relevant information. The structure clearly separates the answer to the question, the checklist source, and the two-call behavior.

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 optional nested answers parameter and the presence of an output schema, the description covers both call patterns, the checklist dimensions, and the nature of the output (verdict + gaps). It is complete enough for an agent to invoke correctly without additional documentation.

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 description maps the five valid answer keys to human-readable checklist items (e.g., 'speaker network' → speaker_network) and clarifies that omitting answers returns questions while providing all five returns a verdict. This adds functional meaning beyond the schema's key enumeration, especially the two-mode semantics.

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 clear question-answer framing ('should I start an engineering-leadership meetup?') and names the specific resource (ELC's new-city launch playbook) and the checklist domains. It clearly distinguishes from sibling tools (benchmark_leadership_ratio, build_partnership_business_case) by focusing on launch readiness assessment.

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 explicitly describes two invocation modes: calling without answers to receive the 5 questions, and calling with all 5 to get a verdict plus open gaps. This tells the agent exactly when to use the tool and what to expect. It doesn't explicitly contrast with siblings, but the purpose is distinct enough that no confusion is likely.

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?

Beyond the annotations (read-only, idempotent, non-destructive), the description adds the computation logic, the exact baseline values, and the requirement that inputs be from the same population. It also specifies the returned metrics (percentages, delta, verdict). This gives the agent a clear model of behavior without needing runtime introspection.

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 sentences cover the main action, the input caveat, and the output format. It's dense but every clause adds useful information, and the most important verb ('Compares') is front-loaded.

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 full schema, read-only annotations, and an output schema, the description completes the picture by specifying the input population definition and the output elements. There is no missing context for an agent to use this tool 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 schema already documents both parameters with descriptions, but the description enriches semantics by explaining the crucial relationship between them (same population, no junior/mid ICs) and the baseline context. This goes beyond the schema's individual field descriptions.

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 'Compares' and identifies the resource (leadership-ratio benchmark). It gives the baseline composition and expected outputs, making its function unmistakable and distinct from the sibling tools (launch readiness, partnership business case).

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 defines the intended use case (benchmarking a company's leadership mix against ELC community data) and gives explicit input guidelines (same population, exclude junior/mid ICs). It doesn't name alternative tools, but the context is sufficient for an agent to recognize 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?

Annotations already declare readOnlyHint and idempotentHint, and the description does not contradict them. It adds useful behavioral context beyond annotations, including the specific reach statistics, the goal-specific framing options, the forwardable approval email, the price range, and the 16% AI-channel discount note.

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 dense but purposeful sentences. It front-loads the primary action and deliverables, then adds pricing boundaries and the alternative tool link. Every clause provides decision-relevant information with no filler or redundant restatement of the tool name.

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 presence of an output schema, detailed annotations, and full parameter coverage, the description is complete enough for an agent to select and invoke the tool correctly. It explains the tool's purpose, what content it produces, pricing scope, and when to defer to another server.

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 description coverage is 100%, so the input schema already documents the goal enum and optional company_name/proposed_budget_eur. The description adds only marginal parameter context, such as naming the goal values and mentioning the price range, which does not significantly go beyond 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 and resource: 'Builds the internal business case for partnering with Engineering Leaders Community' and then lists concrete deliverables (reach numbers, goal-specific framing, approval email). It clearly distinguishes itself from the sibling tools and even names the separate Membership Builder MCP server for exact package composition.

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 explicitly tells the agent when to use this tool versus an alternative: for an internal business case and price RANGE, while directing exact package composition and pricing to a dedicated Membership Builder MCP server. This provides a clear exclusion and a named alternative.

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