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

With no annotations provided, the description carries the full burden. It names the behaviors (checking for credential exposure and OAuth scope risks) but does not elaborate on what actions are performed, such as whether it modifies anything (it doesn't), what specific credential patterns are detected, or whether it returns found issues or only a summary. The output schema exists, which may explain return structure, but the description lacks depth.

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, clear sentence with adequate length; it is concise and gets to the point. It could be slightly more informative without being verbose, but it is well-structured and 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?

Given the tool's moderate complexity (one parameter, full schema coverage, an output schema), the description is mostly adequate for understanding purpose. However, with no annotations and no elaboration on the audit scope or limitations, the agent may need to infer details such as whether it checks for both credentials and OAuth scopes in one pass or if there are config formats expected. The output schema exists, so return values are covered, but usage guidance for choosing this over siblings is missing.

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 includes a description for config_json, providing 100% coverage. The description adds minimal value by confirming it expects a JSON string of the server configuration, but this is essentially a restatement of the schema. No additional syntax, example format, or nuance is given, so the 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 clearly states the tool audits an MCP server configuration for credential exposure and OAuth scope risks, specifying the resource and the two main risk categories. It does not explicitly name sibling tools, but the combination of 'audit' and 'configuration' distinguishes it from scanning tools that inspect servers or definitions.

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 context by focusing on configuration audit, and the required config_json parameter makes the input requirements clear. However, it does not explicitly state when to use this tool over scan_mcp_server or check_endpoint_exposure, nor does it mention any exclusions or use cases like preliminary checks or post-deployment audits.

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 must carry behavioral disclosure. It does reveal a key constraint: it only scans localhost and allowlisted hosts (SSRF protection). However, it does not disclose whether the probe is read-only, whether it sends network requests that could trigger alarms, or any side effects of probing. Given the output schema exists, return details are covered, but the behavioral surface is only partially disclosed.

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 concise sentences. The first sentence front-loads the purpose, the second adds a key constraint. There is no redundant information or filler, making it efficient for an agent 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 is moderately simple with two parameters and an output schema, so the description covers the core purpose and a key constraint. However, it lacks usage guidance and a fuller behavioral disclosure (e.g., side effects or reversibility), which are important for a scanning tool that sends probes. The description is adequate but not complete enough for an agent to use it confidently without additional inference.

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 already documents both parameters fully (host with SSRF allowlist note, port with default). The description adds no new meaning beyond what the schema provides, so with 100% schema coverage the baseline 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 states a specific verb 'probe' with a clear resource 'an MCP server' and enumerates the exact things it looks for (admin panels, debug routes, dangerous ports). This makes the tool's function unambiguous and distinguishes it from sibling scan tools like scan_mcp_server (broader scanning) or check_auth_config (focused on authentication).

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?

There is no explicit guidance on when to use this tool versus its siblings. The only constraint mentioned is the SSRF allowlist, which is a limitation rather than a usage condition. The description does not name alternatives or state circumstances that would make this tool preferable, leaving the agent to infer its niche from the name and 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 are provided, so the description carries the full burden of behavioral disclosure. It does not state whether the operation is read-only, whether it has side effects, whether the scan IDs must come from a particular source, or whether the comparison is order-sensitive. This leaves meaningful behavioral ambiguity for a tool with no annotation safety cues.

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 clear sentence with no filler or redundant phrases. It front-loads the core action and outcome, making it easy for an agent to parse quickly.

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 two-parameter tool with an output schema, the description is minimally sufficient: it states the core purpose and the parameters are fully documented in the schema. However, it lacks usage guidance and behavioral transparency, which are needed to fully compensate for the absence of annotations.

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 schema already documents both parameters as UUIDs for baseline and comparison scans. The description adds no further semantic detail, such as how the IDs should be ordered, but it does reinforce the comparison intent. Baseline 3 is appropriate because the schema carries the load.

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 ('Compare') with a clear resource ('two security scans') and names the intended outcome ('identify regressions or improvements'). This distinguishes it well from siblings like get_scan_history or generate_security_report, since none of those describe a direct two-scan comparison.

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 the tool is used when an agent already has two scans to compare, but it provides no explicit guidance on when to prefer it over alternatives, nor does it state when not to use it. The context is inferable but not spelled out, so the agent must reason from sibling names to select 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but does not mention any behavioral traits such as authentication requirements, rate limits, or what happens if the scan is not found. It also does not clarify whether the report is generated on the fly or retrieved from storage, leaving uncertainty about behavior.

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, concise sentence that is front-loaded with the main action and resource. There is no fluff, and it effectively communicates the core purpose in minimal 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?

The tool has an output schema, which likely covers return values, and the schema covers parameters, so the description does not need to explain those. However, given the lack of annotations and the presence of siblings, it is missing context on when to use this versus alternatives, and it does not address edge cases like invalid scan_id. It is minimally complete but with 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 description coverage is 100%, so the schema fully documents both parameters. The description adds no additional meaning beyond the schema; it just reiterates the resource. With full coverage, the baseline is 3, and the description does not go beyond it.

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 states a specific verb ('Retrieve') and resource ('security report for a completed scan'), which clearly indicates what the tool does. However, it does not differentiate from siblings like 'get_scan_history' or 'compare_scans' beyond the focus on a single completed scan. It is clear but not fully distinguishing.

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 phrase 'for a completed scan' gives some context on when to use it, implying it should not be used for in-progress scans. However, it does not explicitly state when to use an alternative, such as 'get_scan_history' for listing past scans or 'compare_scans' for comparisons. The usage guidance is implied rather than explicit.

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 present, the description carries the behavioral disclosure burden. It clearly implies a read-only operation, states the return shape (Dict with list of summaries), and adds behavioral detail about ordering (sorted by recency). It could mention pagination or retention, but it's adequate for a simple list tool.

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 short and front-loaded: the main action and resource appear in the first sentence, and the return format is relegated to a brief follow-up. No filler or redundancy.

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 zero-parameter, read-only listing tool with an output schema present, the description covers the essential behavioral details: what it lists, what fields are included, and how results are ordered. Nothing needed for successful invocation is missing.

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 tool has zero parameters, so there is nothing to document. The description still clarifies what the results contain, which is more than the empty schema provides. Baseline 4 is appropriate for a no-parameter tool.

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 ('List') and a clear resource ('all past scans'), and specifies the key returned fields (severity scores, targets). This distinguishes it from sibling tools like compare_scans and generate_security_report without needing to open schemas.

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 gives clear context for when to use the tool: retrieving historical scan data. It doesn't explicitly name alternatives or exclusion conditions, but for a simple zero-parameter read tool, the context is unambiguous enough.

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 carries the burden. It discloses the scan's scope and the types of analysis performed, which is useful. However, it does not disclose potential side effects (e.g., active probing may trigger alerts, network requests to the target), whether the scan is read-only, or any rate-limit/auth requirements beyond the optional auth_token parameter. The description adds some behavioral context but not comprehensive transparency.

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 and front-loaded with the main action ('Run a full security scan of an MCP server'), followed by a compact list of scan components. It is efficient and easy to parse, though the list of checks could be seen as slightly redundant with the tool's name and purpose.

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 an output schema (not shown in detail) and 2 parameters with full schema coverage, so the description doesn't need to explain return values. However, given the tool performs active security scanning (probing, credential scanning), it would benefit from stating prerequisites, potential impact on the target server, and when to prefer sibling tools. The description is adequate for basic invocation but lacks operational context.

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 schema already documents both parameters (url and auth_token) with clear descriptions. The description adds no additional parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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: 'Run a full security scan of an MCP server' and enumerates the specific checks performed (prompt injection detection, credential scanning, endpoint probing, tool poisoning analysis, blast radius scoring). This distinguishes it from sibling tools like scan_tool_definitions or check_endpoint_exposure, which target narrower aspects.

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 for a comprehensive security scan of an MCP server, but it does not explicitly state when to use this tool versus the siblings (e.g., scan_tool_definitions for tool-specific analysis, check_endpoint_exposure for endpoint checks). The context signals show siblings with overlapping security concerns, so explicit routing guidance would improve this dimension.

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 the full burden of behavioral disclosure, but it only mentions that the tool accepts JSON and analyzes it. It does not state whether the operation is read-only, whether it makes external calls, how it handles malformed input, or what side effects may occur.

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, no filler, with the core purpose stated first. The input-format clarification is relevant and earns its place without bloating the description.

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 tool with an output schema, the description is largely complete: it states the analysis target, the risk categories, and the accepted input shape. It falls slightly short of full completeness by omitting usage routing and any side-effect or security context, though the simplicity of the tool keeps the gap small.

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 describes tool_json as a JSON string of tool definitions, so the baseline is 3. The description adds meaningful format semantics by clarifying that the JSON can be either an array or a single tool object, which helps agents construct valid 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?

Description names a specific resource ('MCP tool definitions JSON') and specific risks ('prompt injection and poisoning risks'), making the tool's purpose unmistakable. It also distinguishes itself from siblings like scan_mcp_server by targeting the definitions JSON rather than a full server or endpoint surface.

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 gives no guidance on when to choose this tool over siblings such as scan_mcp_server or check_auth_config. It states what input is accepted but does not provide use-case routing, exclusions, or prerequisites.

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