Agent Utility MCP

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral detail: the decision is deterministic, policy-aware, and treats workspace paths outside the root as higher risk. It also explicitly states that arguments are 'analyzed as data and never executed', which is not present 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 two clear, front-loaded sentences. The first sentence defines the tool's function and outcome set, the second adds a specific risk rule. There is no redundant or filler content; every sentence contributes 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?

Given the tool's complexity, the description covers the core purpose, the decision set, policy options, risk categories, and the workspace_root rule. An output schema exists, so return values need not be described. The description is complete and self-sufficient for an agent to determine when and how to invoke 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 description coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining how the 'policy' parameter affects the decision, how 'workspace_root' influences risk assessment, and clarifying that 'arguments' are not executed. This adds meaningful 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's purpose: 'Analyze a proposed AI-agent tool call before execution and return a deterministic, policy-aware decision'. It specifies the exact verb (analyze), resource (tool call), and output (allow, notice, confirm, block). This distinguishes it from sibling analysis tools like analyze_url_risk, inspect_command, and inspect_file, which target different inputs.

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: before executing a tool call to assess risks like 'destructive actions, sensitive-data exposure, external transmission', etc. It mentions the applicable policies and the workspace_root risk factor. However, it does not explicitly name alternatives or state when not to use the tool, so it falls short of 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?

The description adds behavioral context beyond the annotations by stating the decision is deterministic and listing possible outcomes (allow, notice, confirm, block) and the default policy. This complements the read-only and idempotent hints without contradiction.

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 single-sentence description is front-loaded with the action and includes all essential context without redundancy or filler.

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 annotations, complete input schema, and available output schema, the description sufficiently covers purpose, default behavior, and policy options, making it complete for an agent to invoke confidently.

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 all parameters with 100% coverage, so the baseline is 3. The description adds meaning by explaining the policy-aware decision logic and default policy, but it does not detail individual parameters beyond what the schema 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 analyzes URLs for structural and security risk signals and returns a deterministic, policy-aware decision, explicitly distinguishing it from sibling tools that analyze tool calls, commands, or files.

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 use for URL risk assessment and clarifies the default policy, but it does not explicitly state when to use this tool over alternatives or list exclusions. It provides clear context without formal 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 readOnlyHint and idempotentHint. The description supplements this by stating the command is 'without running it' and that path risk is based on workspace_root. These behavioral traits are not fully captured by the annotations, adding valuable context without contradicting them.

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 and front-loads the primary purpose. It packs essential information—decision enumeration, non-execution guarantee, policy options, and path risk—without redundant phrasing. 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?

With an output schema present, the description does not need to explain return values. It adequately covers the decision types, policy defaults, and risk factors. Although it leaves cwd and shell semantics to the schema, the tool context is sufficiently complete for agent selection and 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 100%, so the description need not add parameter-level detail. It does add the default policy ('balanced') and the higher-risk heuristic for paths outside workspace_root, but the schema already documents these. Thus a baseline score of 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 'Analyze a shell command before execution' and enumerates concrete decision outcomes (allow, notice, confirm, block). This clearly identifies the resource as shell commands, differentiating it from sibling tools like analyze_tool_call, analyze_url_risk, and inspect_file, which target other resource types.

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 by stating the tool inspects commands 'before execution' and explains policy options and workspace_root risk. However, it does not explicitly name sibling alternatives or provide when-not recommendations, so it stops short of full usage guidance.

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 substantive behavioral context beyond the annotations: it explains the tool does not execute the file, performs local inspection, and returns specific decision types (allow, notice, confirm, block). This complements the readOnly/idempotent hints with concrete operational details, and there is 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 a single, well-structured sentence that front-loads the core action ('Inspect a Base64-encoded file locally') and efficiently conveys the purpose, safety, and policy aspects without redundant words. 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?

Given the tool's complexity, the description covers essential aspects: what it does, how it behaves (no execution), the decision output, and policy options. The output schema exists, so return values are already documented. The description is sufficient for an agent to understand and invoke the 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?

Schema coverage is 100%, so the baseline is 3. The description does mention the policy options and default, but this largely restates the schema's enum description. It adds minimal information beyond what the schema already provides for filename/content_base64, so no higher score is warranted.

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: inspect a Base64-encoded file locally for structural and security risk signals without executing it, and return a policy-aware decision. It distinguishes itself from siblings by focusing on file inspection and explicitly noting non-execution, which differentiates it from tools like inspect_command or analyze_url_risk.

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 on when to use the tool—for evaluating a Base64-encoded file's risk locally without execution—and mentions the policy parameter. However, it does not explicitly name alternatives or state when not to use it, so it lacks the explicit exclusions that would merit a 5.

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