Conducted MCP

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

The description discloses the return structure (should_log, reason, entry_template) and the rule that confined_to_one_session means no entry needed. Since no annotations are provided, the description carries the full burden; it adequately describes the behavior without contradicting any structured data.

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 concise with three sentences: purpose, input flags, and output structure. It is front-loaded with the core purpose and provides necessary details without extraneous text.

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 no output schema and no annotations, the description covers the essential aspects: input flags, output fields, and the special case for confined_to_one_session. It lacks detailed explanation of each flag's definition but is sufficient for understanding the tool's role.

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 0%, so the description must compensate. It lists all five parameters as 'whichever apply' but does not define what each condition (e.g., gate_resolved_cross_cutting) means. This adds minimal semantics beyond the parameter names.

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 encodes rules for deciding whether a situation belongs in the Decision Log. It lists the boolean flags and explains the return value, making the purpose specific and distinct from sibling tools which involve gates, plans, or validation.

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: when you need to evaluate if a decision should be logged. It provides a specific guideline that a decision confined to one session does not need an entry. However, it does not explicitly exclude use cases or compare with siblings.

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?

Discloses that the server reads no files (agent-supplied content) and details the return shape. Without annotations, it carries the burden well, though it does not mention idempotency or side effects (likely none). No contradictions.

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 rule, no unnecessary words. Every sentence adds critical information: rule, input options, output shape, and server 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?

Covers all essential aspects: purpose, input alternatives, parsing behavior, output structure, and server constraint. Without an output schema, the description fully defines return values. Complete for the tool's complexity.

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 descriptions are present for both parameters (100% coverage). The description adds value by explaining the parsing of markdown checkboxes and the mutual exclusivity implicit in the alternatives, going beyond 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?

Clearly states the verb (evaluate), resource (goal brief gates), and the rule it encodes. Distinguishes from sibling tools like kickoff_plan or decision_log_guidance by specifying gate resolution for session starts.

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?

Explicitly provides two input alternatives (structured gates list or content string) and explains the parsing behavior. Implies usage context via the rule about session start, but does not explicitly state when not to use or what alternatives exist.

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?

With no annotations, the description fully discloses behavior: it assembles files from templates, replaces tokens, reports missing tokens, never overwrites (idempotent), and returns files with actions without writing to disk. This is comprehensive and addresses safety (no writes) and constraints (D5 strict).

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 paragraph with every sentence providing essential information—purpose, inputs, output structure, idempotency, and conditions. It is efficient and front-loads the main action.

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?

Despite having no output schema, the description fully explains the return value structure (files, missing, open_questions, warnings) and the success condition. All input parameters are contextualized, and behavioral nuances (idempotency, token resolution) are covered, making it complete for an agent.

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%, baseline 3. The description adds value by explaining that answers are keyed by token id, detected holds brownfield facts, and existing is the agent's file inventory, providing context beyond the schema field names.

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 starts with a specific verb 'Assemble' and lists exactly which files are produced (four _template.md copies, decision-log.md, AGENT_CONVENTIONS.md), clearly distinguishing from siblings like kickoff_questions (for gathering answers) or decision_log_guidance (for format 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?

It indicates required inputs (project_type, answers) and optional ones (detected, existing), implying use after interview answers are collected. It also states the ready condition (missing empty) and idempotency, but does not explicitly exclude alternatives or mention when not to use this tool versus siblings.

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?

With no annotations, the description carries the full burden. It discloses nondestructive behavior (server reads no files), explains the branching logic, and describes the return fields. It could be improved by explicitly stating there are no side effects, but overall it is informative.

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 paragraph but packs essential information: main purpose, branching logic, special case, return type, and a behavioral note. Every sentence adds value, and the structure is logical.

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?

Without an output schema, the description explains the return fields (project_type, questions, inferred, notes). It also covers the logic for both project types and notes the server reads no files. This is complete for the tool's complexity.

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 100% description coverage, but the description adds meaning beyond the schema. It explains how project_type affects behavior, that detected is for brownfield only, and that LOCKED_DOCS is always asked. This provides significant context for parameter 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 returns the branched kickoff interview questions based on project_type. It specifies behavior for greenfield vs brownfield and mentions the return object structure. It is distinct from siblings like decision_log_guidance or kickoff_plan, 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 explains when to use greenfield vs brownfield and notes the special case of LOCKED_DOCS always being asked. It provides clear context for usage but does not explicitly mention when not to use the tool or discuss alternatives among siblings.

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?

With no annotations provided, the description carries full burden and exceeds expectations. It discloses that the server reads no files (safe, fast), the output originates from bundled guides and conventions, and the exact return structure. No destructive or hidden behaviors are omitted.

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 zero waste. The first sentence states the core purpose; the second packs in parameter guidance, output shape, source, and a behavioral guarantee. Essential information is front-loaded and every sentence 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 tool with 2 parameters and no output schema, the description fully compensates by specifying the return shape, sourcing, and behavior. It covers all relevant aspects: what the tool does, when to use it, what parameters mean, what output to expect, and a safety guarantee (no file reads). No 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?

Schema coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by listing the enum values inline, providing an example fact (ticket id), and explaining that facts 'tailor the output.' This extra context helps the agent understand parameter usage beyond the schema's 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 clearly states the tool returns the ordered procedure for a methodology phase. It lists the valid phases, the output structure, and distinguishes from sibling tools like validate_artifact by noting it is 'the procedure half of advisor + validator.' The verb 'Return' plus resource 'ordered procedure for a methodology phase' is specific and unambiguous.

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 when to use the tool: when the agent needs the procedure for their current phase in the methodology loop. It provides context about the tool's role as the procedure half of advisor/validator, implying complementarity with sibling tools. However, it does not explicitly state when not to use it or name alternative tools.

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?

With no annotations provided, the description fully bears the transparency burden. It discloses the priority logic for triggers, clarifies that working days are an input not a computation, and specifies the return structure ({ due, reason, detail }). No contradictions or hidden behaviors.

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 concise sentences, each serving a distinct purpose: purpose statement, logic explanation, and caveat about working days. No fluff, every sentence 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 moderate complexity (5 parameters, no output schema, no annotations), the description covers the core logic, output shape, and a key behavioral note. It omits error handling or input validation details, but for a judgment tool without required fields, it is adequately 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?

Schema coverage is 0%, so the description must compensate. It explains the role of each parameter (e.g., gate_reached triggers 'gate', working_days_since_last_standup triggers 'weekly') and clarifies that working_days_since_last_standup is an input. Though date formats are unspecified, the description adds significant meaning beyond the raw 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 clearly states the tool's purpose: 'Given agent-supplied facts, decide whether a standup is due.' It specifies the verb (decide) and resource (standup due) and differentiates from siblings by detailing the exact logic and output format, leaving no ambiguity.

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 explains the decision logic but does not explicitly state when to use this tool over siblings like 'evaluate_gate' or 'decision_log_guidance'. Usage is implied (when needing to determine if a standup is due), but no exclusions or alternatives are provided.

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?

No annotations provided, so description fully handles disclosure. Explains return structure (valid, missing, warnings) and behavior: missing is blocking, warnings advisory, server never reads files. Could mention sync/async or performance.

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?

Compact yet thorough. Sentences are front-loaded with primary action, followed by usage note, then detailed return format. No unnecessary words.

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 no output schema or annotations, description fully explains tool's purpose, input, return values, and behavioral semantics (blocking vs warning). No gaps.

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 covers parameters at 100%, but description adds context: 'full text' and 'server never reads files', clarifying input requirements and file-handling behavior.

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?

Specific verb 'check' and resource 'artifact's text'. Clearly states it validates Conducted Development artifacts against methodology structure. Distinct from sibling tools like evaluate_gate or kickoff_plan.

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?

Explains how to use: supply artifact_type and full text. Implicitly differentiates from siblings but does not explicitly compare or state when not to use.

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