Count tokens, apply an optional model-aware budget, and redact likely credentials locally. Inputs over 12,000 characters require the paid HTTP API.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text or code to preflight. | |
| model | No | Optional model name. | |
| redact | No | Redact likely credentials. | |
| token_budget | No | Optional hard token budget. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses that redaction happens locally and that there is a size-dependent API requirement. However, it does not describe the output format, whether the input is modified, or what happens when the budget is exceeded, leaving gaps.
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 sentences: the first lists the core functions, the second a key constraint. Every word earns its place, and the most important information 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 explains the tool's main operations and a size limitation, but without an output schema, it fails to clarify what is returned. It also omits edge-case behavior (e.g., empty input, budget enforcement mechanics). For a tool of this complexity, more detail is needed to be fully 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 coverage is 100%, but the description adds valuable nuance: 'model-aware budget' explains how token_budget interacts with the model parameter, and 'locally' clarifies that redaction is client-side. These additions go beyond the schema's basic field descriptions, providing meaningful context.
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 three specific functions: counting tokens, applying a model-aware budget, and redacting credentials. This is a specific verb+resource definition that matches the tool name and leaves no ambiguity about its purpose.
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 clearly implies when to use the tool (whenever token counting, budgeting, or redaction is needed) and mentions a critical usage constraint (12,000-character threshold requires paid API). However, it does not explicitly discuss alternatives or exclusions, which would push it to a 5.
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.
Each tool addresses a completely distinct concern: IP reputation lookup, token/context preflight, and web page preview. There is no realistic scenario where an agent would confuse these tools for one another.
All names are clean and snake_case, but the naming styles are mixed: 'ip_intel' is noun-noun, 'preflight_context' is modifier-noun, and 'read_page_preview' is verb-noun. The names are readable but do not follow a single predictable convention.
At 3 tools, the server is compact and every tool has a distinct, useful responsibility. The count feels appropriate for a focused utility API with no obvious excess or bloat.
The tools are self-contained for their advertised free/local behavior, but the set feels more like a small grab-bag than a complete agent-context domain. For instance, read_page_preview only expose an exact preview slice and points to a paid full-page API outside the MCP server, creatinga notable limitation. Broader workflow suchs as batch preprocessing, full-context retrieval, or history/lifecycle management are not present.