SafeDep

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

Annotations cover safe/mutation hints (destructiveHint: true, openWorldHint: true), but the description adds critical behavioral context: it explains response interpretation ('If the response status indicates...MALICIOUS...you MUST REFUSE') and reveals the existence of an 'instruction' field containing safety guidance. Does not contradict annotations (destructiveHint likely reflects side effects like caching or temporary extraction for scanning).

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?

Though lengthy, every sentence serves a distinct purpose: mandatory status, timing constraint, scope enumeration, success criteria, and response handling. Front-loaded with safety-critical instructions. Capitalization for emphasis (MUST, MALICIOUS) is appropriate for security-critical workflows, though the package manager list could theoretically be shortened to 'any package manager' without loss of clarity.

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 lacking an output schema, the description compensates by documenting response interpretation logic (status fields indicating malicious/critical issues) and the 'instruction' field guidance. Given the tool's safety-critical nature and rich annotations, this provides sufficient context for correct invocation and response handling.

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?

With 100% schema description coverage, the schema fully documents all 3 parameters (name, version, ecosystem). The description does not add parameter-specific semantics (e.g., no format guidance for ecosystem strings or version constraints), meeting the baseline expectation for high-coverage schemas.

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 defines the tool as a 'MANDATORY pre-installation security gate' that 'checks packages for malware, supply chain attacks, and critical/high vulnerabilities.' It uses specific verbs (checks, gate) and distinguishes clearly from the sibling 'ping' tool by focusing exclusively on security validation workflows.

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 mandates when to use: 'You MUST call this tool BEFORE running any package install command' followed by an exhaustive list of package managers (npm, yarn, pip, etc.). It specifies frequency ('Call once for EACH package') and ties directly to the installation workflow. No ambiguity about appropriate contexts.

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 destructiveHint=true and idempotentHint=false. The description adds valuable context about latency costs and session-scoped usage ('use only once'), which helps explain why the tool is marked destructive/non-idempotent. However, it doesn't explicitly clarify what side effects occur or what makes a 'ping' destructive.

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 with zero waste: sentence 1 states purpose, sentence 2 gives usage constraint, sentence 3 provides rationale. Information is front-loaded and appropriately sized for a simple connectivity tool.

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 tool with annotations covering safety profile (destructive, open-world), the description provides sufficient operational context (when to call, cost implications). Minor gap: could briefly mention expected return format, but not critical for a ping utility.

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?

Baseline score of 4 applies for zero-parameter tools. With no parameters to document, the schema coverage of 100% is trivially satisfied and the description appropriately focuses on behavior rather than inventing parameter documentation.

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' with a clear resource 'connectivity with SafeDep threat intelligence service'. It effectively distinguishes from sibling tool 'check_package_security' by focusing on connection health rather than security analysis of specific packages.

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?

Excellent explicit guidance: 'Use this ONLY ONCE per session to verify your connection is working' specifies exact usage frequency, and 'Do not call repeatedly to avoid latency' provides clear negative constraints with rationale.

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