Everything in the standard report, plus a repo-wide secret/credential exposure scan (matched values are never returned).
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | Optional branch/tag to analyze. Defaults to the repository's default branch. | |
| repo_url | Yes | Public https://github.com/... or https://gitlab.com/... repository URL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral transparency burden. It uses that space to guarantee that matched secret values are never returned, which is a meaningful output-privacy behavior beyond the schema. It also indicates the scan is repo-wide. It does not mention auth, runtime, or side effects, but the redaction guarantee is valuable.
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 entire description is one well-structured sentence that front-loads the relationship to the standard report and appends the key caveat. There is no filler and no repetition of schema information.
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 the essential selection point (deep vs standard) and the key redaction behavior. However, it does not describe the report's return format or how this tool compares with the due_diligence sibling. With no output schema and no annotations, a bit more context about what the agent receives would improve completeness.
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 with 100% coverage, so the baseline is 3. The description adds no parameter-specific syntax or constraints; 'repo-wide' and 'standard report' are tool-scope context rather than parameter semantics.
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 names a concrete deliverable (repo risk report) and adds the differentiating secret/credential exposure scan, so an agent can distinguish it from the standard variant. It never states a direct verb like 'generates' or 'returns', relying on the tool name and 'report' for the action. Still, the resource and extra feature are clear.
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 'Everything in the standard report, plus...' signals that the deep variant is for situations where a standard repo risk report should also include a secret/credential scan. This gives a clear context for choosing this tool over the standard report. It does not explicitly say when not to use it or how it relates to the due_diligence sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools occupy the same security-audit space: get_dns_lookup/get_domain_intelligence, get_security_posture/get_web_audit/post_domain_due_diligence, and the three post_security_repo_risk_report variants heavily overlap. Video generation is split only by duration, and get_ssl_check/get_security_posture both target TLS/certificate concerns, so an agent could easily select the wrong tool.
All tools use snake_case and a get_/ post_ prefix, which is a recognizable convention and generally readable. However, the suffix order is inconsistent (get_url_parse vs get_security_posture vs post_security_repo_risk_repport_standard), and get/post are HTTP-style prefixes rather than semantic verbs, so the pattern is only partially coherent.
34 tools is well above the 'too many' threshold and spans unrelated domains: domain security, repo risk, JSON/hash/text utilities, media generation, Quebec invoices, and x402 payments. Many tools are variants that could be consolidated (video durations, risk report tiers, audit scopes), so the count feels inflated rather than purposeful.
The set lacks a single apparent domain, so no complete lifecycle is clearly covered: video generation has no status/retrieval, repo risk reporting is read-only, and common companions (URL encoding, current timestamp, image analysis) are missing. It is a broad collection of one-off utilities rather than a coherent functional surface.