Shadow AI List

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

Annotations already declare readOnlyHint=true, and the description adds useful behavioral details beyond that: it returns the matched tool and risk, and only if matched. It also discloses coverage ('Covers the free top 100'), which is a meaningful limitation. It does not describe no-match behavior or edge cases, but for a safe read-only tool this is reasonable.

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 focused sentences. The first states the action and purpose, the second adds return behavior and scope. No filler or redundant content, and it 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?

For a single-parameter, read-only tool with no output schema, the description covers the key points: what it checks, what it returns when matched, and its coverage limit. Minor gaps include the exact output structure and behavior when no match is found, but these are not critical for tool selection.

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% coverage with a clear parameter description and example ('A domain or URL, e.g. "chat.openai.com" or "https://cursor.sh"'). The description adds no additional parameter semantics beyond the schema, so the baseline of 3 applies.

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 ('Check whether') and clearly identifies the resource ('domain or subdomain belongs to a known AI tool'). It distinguishes itself from siblings by being domain-oriented rather than listing or top-risk oriented, and adds scope ('Covers the free top 100').

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 clearly implies when to use the tool: when you have a domain/URL and want to determine if traffic to it is shadow AI. It does not explicitly name alternatives or when-not-to-use scenarios, but the context is unambiguous enough for an agent to select it appropriately.

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 the description adds the 'free top 100' scope and notes the returned fields (name, domain, category, risk score + band). This provides some context beyond annotations, but does not disclose other behaviors like pagination or rate limits. It adds moderate value 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 description is three short, front-loaded sentences: purpose, return fields, and scope. Every sentence adds distinct value with no 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?

For a simple read-only list operation with one optional parameter and no output schema, the description covers return fields, the sorting basis (highest risk), and the universe (free top 100). It is sufficiently complete, though it could mention sorting order or limit behavior explicitly.

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% coverage for the only parameter 'limit', including default and max, so the description does not need to elaborate. The description adds no additional parameter context, keeping the baseline score of 3.

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 highest-risk AI tools ranked by AI Exposure Index risk score. It specifies the resource (AI tools), the metric (risk score), and the output fields, distinguishing it from siblings that list all shadow AI or look up specific 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?

The description implies usage when you need a ranked list of risky AI tools, but does not explicitly mention when to prefer this over sibling tools like list_shadow_ai or lookup_ai_tool_risk. No exclusions or alternative guidance are provided, so guidance is only implied.

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 openWorldHint=false, so the read-only nature is established. The description adds useful context beyond annotations by clarifying the result scope ('Covers the free top 100') and the output fields, which is valuable given no output schema.

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 extremely concise: two sentences with no fluff. It front-loads the primary action and includes relevant output details and scope in the second sentence.

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 list tool with complete schema coverage, annotations, and no output schema, the description provides enough context: what is returned, optional filtering, and scope. It could be slightly more explicit about ordering or pagination, but the current description is sufficiently complete for 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?

The input schema has 100% parameter coverage with descriptions for both limit and category. The description reiterates category filtering but does not add extra semantic meaning beyond the schema, such as behavior of the limit default or category examples.

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: listing AI tools from the registry with optional category filtering. It specifies the returned fields (name, domain, category, risk band) and scope (free top 100), which distinguishes it from sibling tools like lookup_ai_tool_risk that target specific lookups.

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 it: when you need a list of AI tools from the registry, optionally filtered by category. However, it does not explicitly mention alternatives or exclusion cases, such as using lookup_ai_tool_risk for a specific tool or get_top_risky_ai for risk-focused ranking.

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 the description adds useful behavioral context: the 'free top 100' coverage limitation, which affects results when the tool is not in that set. It does not contradict annotations. It goes beyond simple read-only disclosure with this scope constraint.

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 concise sentences. The first states purpose and outputs, the second states the coverage limit. No unnecessary words, front-loaded with the action and resource.

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 param, no output schema, no nested objects), the description is complete. It lists all key return fields and the coverage limitation. An agent can confidently invoke the tool based on this description alone.

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%, and the query parameter description already explains the accepted values. The tool description restates 'name, vendor, or domain', which matches the schema, but adds no new parameter-specific meaning beyond what the schema provides. 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 uses the specific verb 'look up' and clearly identifies the resource (AI tool) and the exact data returned (risk score, risk band, category, training on user data). It distinguishes itself from siblings like list_shadow_ai or get_top_risky_ai by focusing on querying a specific tool by name/vendor/domain.

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 clear usage: use this when you need risk details for a particular AI tool by name, vendor, or domain. It provides context without explicit alternatives or exclusions, but the scope limitation ('free top 100') gives practical guidance. It does not name sibling tools as alternatives, so not a 5.

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