Sign yourself up for a developer key without leaving MCP. The email is contact and recovery, not a wall. One key per email, free tier (100 checks a month); the key is in this response and never shown again. Nothing on knowngate.com itself needs a key.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_name | Yes | Who is signing up, e.g. your product name | |
| contact_email | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations show readOnlyHint=false and idempotentHint=false, meaning the tool performs a write and is not idempotent. The description adds important behavioral traits: the response contains the key only once ('never shown again') and one key per email, making the non-idempotence concrete. It also clarifies the key's scope (nothing on knowngate.com needs a key), which goes beyond annotations.
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 concise sentences, each adding distinct value: what it does, limitations/behavior, and scope clarification. Front-loaded with the core purpose, then efficient details. No fluff or repetition of schema properties.
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 2-parameter tool with no output schema, the description covers the essential return value (the key is in the response, never shown again) and the constraints (one per email, free tier). Missing details like rate limits or exact response format are compensated by the explicit 'key is in this response' statement. Sibling tools are check_* functions, so register is clearly the onboarding prerequisite.
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 50%, with contact_email having a description but agent_name only having an example placeholder ('e.g. your product name'). The description adds meaning by explaining contact_email is for contact and recovery, not a wall, which supplements the schema's sparse description. It could have described agent_name more, but the schema's example is adequate.
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 specific verb ('Sign yourself up') and resource ('developer key'), with additional context about free tier and usage limits. It distinguishes from sibling tools by mentioning 'without leaving MCP' and noting what doesn't need a key.
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?
Description provides clear context for when to use (when user requests a developer key) and implicitly suggests it as a prerequisite for the sibling check tools. It doesn't explicitly name alternatives, but siblings are distinct enough that no exclusions are needed; the 'without leaving MCP' and free tier details help an agent decide.
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.
check_item, check_plan, and check_venue are cleanly separated by scope: a single food, a batch/plan up to 25 items, and a venue-level chart. register is clearly the auth/key-creation step and cannot be confused with the checking operations.
The three core tools follow a consistent check_<noun> snake_case pattern, which makes their behavior predictable. register is a clear, conventional name but breaks the verb_noun pattern, so the set is not perfectly uniform.
Four tools is a well-scoped set for this server: one necessary registration step plus three checking operations at increasing levels of granularity. Each tool has a distinct purpose and nothing feels redundant or bloated.
The checking surface is essentially complete: single items, composite plans, and venue charts are all covered, and register provides the required key. The only notable gap is that household premise/restriction configuration is not exposed through MCP, so agents must rely on that being set up outside the server.