No-Shell Agent Architect MCP

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

No annotations are provided, so the description must carry the full burden. It does not disclose whether the tool is read-only, if it has side effects, or any permission or rate limit information. The criteria for scoring are stated, but the behavioral impact is unclear.

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?

A single, direct sentence that efficiently conveys the tool's action and key criteria. No superfluous 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?

Given no output schema, the description should hint at the nature of the 'score' (e.g., numbers, categories) but does not. It also lacks context on input requirements beyond minLength, making it incomplete for an agent to fully understand the tool.

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 one parameter described as 'Automation plan or prompt to audit.' The description adds no additional meaning beyond the schema, so baseline 3 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 specifies the exact verb 'Score' and the resource 'existing automation plan', and lists specific criteria (shell-risk, missing inputs, etc.). It clearly distinguishes from sibling tools that build or design plans.

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?

No guidance on when to use this tool or when to choose an alternative. The description only states what the tool does, without context on prerequisites, exclusions, or comparison to 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?

No annotations provided, so the description must carry the behavioral burden. It only mentions generating a questionnaire, omitting details like permissions, side effects, output format, or whether the questionnaire is returned immediately. For a tool with no annotations, this is a significant gap.

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?

A single sentence of 16 words—extremely concise and front-loaded. However, it sacrifices necessary details; a bit more context would improve without losing efficiency.

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 simplicity (one optional param, no output schema, no annotations), the description is incomplete. It does not explain what happens after generation (e.g., returns a questionnaire, stores it, initiates a process), nor how it fits with sibling tools like build_validation_pack or recommend_agent_tools.

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 sole parameter 'goal' has no schema description (0% coverage) and the description does not explain what 'goal' means or how it affects the questionnaire. The description adds no value beyond the schema, leaving the agent without guidance on what to input.

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 action (generate), the resource (10-minute intake questionnaire), and the target user (non-developer wanting one workflow automated). This distinguishes it from sibling tools like audit_automation_plan or design_automation_stack, but could be more specific about the questionnaire's purpose.

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?

Implies usage for non-developers with a single workflow automation need, but provides no explicit when-not-to-use instructions or comparisons to sibling tools (e.g., when to use build_customer_intake vs. audit_automation_plan).

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 must fully disclose behavioral traits. It only states that the tool creates a contract and mentions output formats. It does not reveal whether the action is destructive, what permissions or side effects exist, or how the output is structured. The description is too sparse to ensure safe and correct invocation.

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 efficient sentence that front-loads the main purpose. It is not verbose and contains no filler. While it could benefit from additional structure (e.g., bullet points on usage), it earns its place and is easy to parse.

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 8 parameters and no output schema. The description provides some context (target users, output types) but does not fully explain the output structure, return values, or behavioral implications. Given the complexity, a more thorough description would help an agent understand what to expect after invocation.

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 75%, meaning most parameters have inline descriptions. The tool description adds no extra meaning beyond what the schema already provides (e.g., goal, domain, userType). Since coverage is high, the baseline of 3 is appropriate; the description does not improve parameter understanding.

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 creates a machine-readable package contract for integrating the No-Shell operating pack via MCP/API, targeting specific user types (agencies, SaaS builders, agents). The verb 'Create' and resource 'package contract' provide specificity, and the mention of human-readable artifacts adds clarity. While it does not explicitly differentiate from siblings, the purpose is sufficiently clear.

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 no explicit guidance on when to use this tool versus its siblings or alternatives. It implies usage in integration contexts but lacks any direct comparison, exclusion criteria, or prerequisites. The agent receives no help in deciding between this and similar tools like audit_automation_plan or build_customer_intake.

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 are provided, so the description must carry the full burden of behavioral disclosure. It only states the tool 'returns' criteria, implying it is non-destructive and read-only, but does not confirm idempotency, side effects, or required permissions. This is minimal transparency for a tool that could potentially be involved in validation processes.

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 sentence with no extraneous content, which is concise. However, it is under-specified for a tool with three parameters and no other documentation. Front-loading is present but at the cost of completeness.

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 (three parameters with no schema descriptions, no output schema, no annotations), the description is severely incomplete. It does not specify what the returned criteria look like, how parameters affect the output, or any usage context. This requires the agent to infer too much.

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 three parameters (goal, risk, domain) with 0% description coverage, and the tool description provides no explanation of how these parameters are used. The phrase 'for one automation workflow' hints at the goal parameter but does not clarify the role of risk and domain. The description fails to add any meaning beyond the schema's type constraints.

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 a specific verb 'Return' and identifies the resource as 'dry-run, QA, audit, and PASS criteria for one automation workflow.' This clearly indicates the tool's output and scope, distinguishing it from sibling tools like 'audit_automation_plan' which likely focuses on auditing rather than building validation packs. However, it lacks detail on what exactly 'PASS criteria' entails, preventing a perfect score.

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?

No explicit guidance on when to use this tool versus alternatives. The description does not mention prerequisites, conditions, or situations to avoid. A sentence like 'Use this when you need to generate validation criteria before running a workflow' would significantly improve the score.

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 bears full burden. It describes outputs but omits behavioral traits: no mention of side effects, permissions requirements, rate limits, or whether the operation is read-only. The word 'turn' suggests processing but lacks safety disclosure.

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?

Single sentence that is front-loaded, listing all deliverables compactly. No filler or redundancy. Could be slightly clearer on the output structure, but it is efficiently 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?

With 6 parameters, no output schema, and no annotations, the description is too vague. It lists output components but does not explain what each means, how they relate, or what the response looks like. Sibling tools exist, but no guidance on coordination.

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 67%, moderate. The description only hints at 'goal' via 'vague automation request' and does not clarify the meaning of risk, domain, language, or other parameters. The description adds marginal value 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?

Description uses a specific verb ('turn') and resource ('vague automation request') and lists concrete output components (tool/MCP/plugin/skill stack, etc.), clearly distinguishing it from siblings like audit_automation_plan or build_validation_pack.

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?

No explicit guidance on when to use this tool versus alternatives. The description implies it's for vague requests but does not state conditions, prerequisites, or when to prefer sibling 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?

Without annotations, the description must disclose behavior. It only states the output is a 'copy-paste natural-language command' and mentions avoiding an empty shell. There is no information about side effects, required permissions, rate limits, or what happens to the input. The tool name suggests it avoids shell execution, but this is not explained.

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 18-word sentence that conveys the core purpose efficiently. It is front-loaded with key information and contains no redundant or filler content.

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 has 6 parameters, no annotations, and no output schema, the description is insufficient. It does not explain what a 'no-shell prompt' is, what the output looks like, or how parameters like 'userType' and 'currentTools' affect the result. The agent lacks enough context to use the tool effectively.

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 67% (4 of 6 parameters have descriptions), so baseline is 3. The tool description does not add any parameter-specific detail beyond the schema. It mentions 'goal' as required but does not elaborate on how to use risk, domain, language, etc. However, the schema itself provides some guidance.

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 that the tool creates a copy-paste natural-language command to instruct an agent, and mentions avoiding empty shell output. This distinguishes it from sibling tools which focus on auditing, building packages, or designing stacks. However, it could be more precise about the type of workflow automation.

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 no guidance on when to use this tool versus alternatives like recommend_agent_tools or build_validation_pack. No context about prerequisites, appropriate scenarios, or exclusions is given.

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 carries full burden. Only states the recommendation action but does not disclose any behavioral traits (e.g., whether it modifies anything, requires specific permissions, or has 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?

Single sentence with clear action and target resources, no filler. Could be improved by front-loading the purpose more explicitly, but currently no waste.

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 6 parameters and no output schema, description is too brief. Does not explain how recommendations are generated, what the output format is, or how parameters like 'currentTools' or 'userType' affect results. Missing critical context for effective use.

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 has 67% description coverage, leaving 2 parameters undocumented. The description adds no information about parameters; it does not explain how 'goal', risk', or others influence recommendations. Baseline adjusted downward due to incomplete schema coverage and zero contribution from description.

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?

Description uses specific verb 'Recommend' and lists exact resource types (MCP servers, Codex plugins, skills, etc.), clearly distinguishing from sibling tools like audit_automation_plan or build_customer_intake which have 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?

No guidance on when to use this tool versus alternatives; does not mention prerequisites, exclusions, or context for when to use recommend_agent_tools over design_automation_stack or generate_no_shell_prompt.

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