AgentSec MCP

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

With no annotations, the description carries full burden. It discloses caching (10 minutes) and cost ($0.01 per call), which adds value beyond the basic purpose. It does not cover rate limits or auth, but for a simple read-only lookup, this is sufficient 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?

Three sentences, each earning its place: first sentence states purpose, second adds detail, third adds behavioral notes. No wasted words, and critical info 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?

The description covers return values and behavioral aspects, but fails to explain how to provide the required input (package/version or CVE ID), given that the schema has no parameters. This omission makes the tool definition incomplete for an agent to invoke 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?

The input schema has zero parameters, but the description implies the tool accepts a package+version or CVE ID. This is a significant discrepancy; the description adds misleading information instead of clarifying how to provide input. With 0 parameters, baseline is 4, but the mismatch makes the description harmful, not helpful.

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 ('look up') and the resource ('CVE vulnerabilities'), specifying the scope as either a npm package+version or a CVE ID. It effectively distinguishes from siblings like 'reputation_check' and 'secret_scan', 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 implies usage for vulnerability lookups by stating what it returns, but it does not explicitly provide when-to-use or when-not-to-use guidance, nor does it mention alternatives. Sibling tools are different, so the lack of exclusions is acceptable but not a strength.

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. It discloses conservative verdict policy (unknown never clean), caching duration (10 minutes), and cost ($0.01 per call), providing rich behavioral context.

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?

Three sentences, each earning its place: purpose, verdict details, and behavior/cost. Front-loaded with actionable information, no wasted 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?

While behavioral details are provided, the description lacks an input parameter specification (IP/domain), making the tool's usage ambiguous. No output schema exists, and the description does not clarify the structure of confidence signals.

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?

Input schema has zero parameters, but description implies the tool accepts an IP or domain as input. This contradiction makes the description misleading. Schema coverage is vacuously 100%, but description adds incorrect information.

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 checks reputation of an IP or domain using specific sources (AbuseIPDB, VirusTotal) and returns a security verdict. It is distinct from sibling tools cve_lookup and secret_scan.

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 does not explicitly state when to use this tool versus alternatives, nor does it provide when-not-to-use guidance. However, the context of security reputation checking is clear from the description.

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. It clearly discloses privacy guarantees (no logging/caching/storage/forwarding), return behavior (only counts and offsets), pattern types, rate limits, and cost, which is highly transparent.

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 four sentences covering purpose, privacy, return details, pattern list, and cost/limits, front-loaded with the primary function.

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 covering many aspects, the description fails to specify how the text content is provided to the tool since the input schema is empty. This is a significant gap for a tool that scans input text, making it incomplete.

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 zero parameters, so the description does not need to explain individual parameters. With no parameters, the baseline is 4, and the description adds no param-specific info, which 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 scans text for hardcoded secrets using 20 patterns, which is a specific verb+resource. It is distinct from sibling tools cve_lookup and reputation_check.

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 does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions. It implies usage for secret scanning but lacks guidance on comparative scenarios.

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