AgentSec MCP

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

No annotations provided, so description carries full burden. It discloses caching (10 minutes), cost ($0.01), and data sources (NVD and OSV). However, does not mention rate limits or authentication needs.

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?

Four sentences, each adding distinct value: purpose, input options, return contents, caching, cost. Efficient but could be slightly more concise.

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 parameters and no output schema, the description adequately explains inputs (package+version or CVE ID), outputs (CVSS, descriptions, fix versions), and operational details (caching, cost). Somewhat complete.

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 0 parameters and 100% coverage, so baseline is 3. Description does not need to add parameter details.

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 specific verbs ('Look up') and resources ('CVE vulnerabilities for an npm package+version or a specific CVE ID'), clearly distinguishing from siblings like reputation_check 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?

It states when to use (to look up CVEs for npm packages or CVE IDs) and mentions cost ($0.01 per call), but does not explicitly say when not to use or suggest 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?

No annotations provided, so description carries full burden. Discloses conservative verdict ('unknown' never 'clean'), caching (10 min), and cost ($0.01 USDC per call). This is good behavioral 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 adding distinct value: what it does, verdict details, behavioral traits. 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?

Given no output schema, the description covers return value (verdict) well. Missing input format details (how to provide IP/domain), but schema has no parameters, so tool may use a different mechanism (e.g., user prompt).

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 no parameters, so the description doesn't add param info. However, schema coverage is 100% (no params), so baseline is 4, but a 3 is reasonable because the tool expects input (IP/domain) not captured in 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?

Clearly states it checks reputation of IP/domain using two services (AbuseIPDB and VirusTotal) and returns a security verdict. Distinguishes from siblings (cve_lookup, secret_scan) which are for 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?

Describes verdict types and caching behavior. Does not explicitly say when to use versus alternatives, but the context (siblings are different) implies it's the go-to for reputation checks.

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?

Discloses critical behavioral traits: no logging/caching/storage of input, returns only counts and offsets (not matched values), rate limit, and pricing. No annotations provided, so description carries full burden and does so excellently.

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?

Extremely concise: 5 sentences covering purpose, privacy, patterns, rate limit, and cost. No filler. Front-loaded with main action.

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 and no annotations, description provides complete context: what it scans, privacy protections, pattern list, rate limit, and cost. No 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?

Input schema has no parameters (empty object), so description doesn't need to add param details. Baseline for 0 params is 4. Description focuses on behavior instead, 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?

Description clearly states the tool scans text for secrets/keys/credentials using 20 patterns. Differentiates from siblings (CVE lookup, reputation check) by specifying unique function.

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?

Explicitly mentions privacy guarantee and rate limit (100/min), and payment cost. Does not explicitly state when NOT to use, but context from siblings and clear purpose implies usage scenarios.

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