get_api_uptimeGet uptime percentage and latency (median + 95th percentile) for an API over the last 24 hours, 7 days, 30 days, and 90 days. Use this for reliability questions like 'how reliable has Stripe been this month?'.
| Name | Required | Description | Default |
|---|---|---|---|
| api | Yes | API name or slug, e.g. 'stripe', 'openai'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safe read-only/idempotent profile. The description adds valuable context about the exact behavioral output—historical uptime and latency percentiles across multiple periods—which is especially useful because there is no output schema. No contradictions or missing safety disclosures.
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?
Two sentences deliver the core action, output metrics, time ranges, and a use-case example with no filler. 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?
For a simple read-only lookup with one parameter, the description covers input, output shape, time granularity, and an example use case. It does not specify latency units or response format, but those are minor given the simplicity and no output schema.
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%: the only parameter, 'api', is documented with a type and example in the schema. The description mentions an API name but adds no meaning beyond the schema, so the baseline score of 3 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?
The description uses a specific verb ('Get'), identifies the resource ('API'), and precisely defines the output (uptime percentage plus median and 95th percentile latency) and time windows (24h, 7d, 30d, 90d). This clearly differentiates it from siblings like get_api_status or list_recent_incidents by focusing on historical reliability metrics.
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 explicitly says to use this for reliability questions and gives a concrete example ('how reliable has Stripe been this month?'). It provides clear context for when to use it, though it does not explicitly state when to prefer an alternative such as get_api_status.
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.
Most tools have clear, distinct purposes: listing monitored APIs, checking individual status, checking multiple statuses at once, and retrieving uptime history. The only ambiguity is between check_apis and list_apis, as both return status information, though one targets specific APIs and the other provides a broader directory.
All tool names follow a consistent snake_case verb_noun pattern: check_apis, get_api_status, get_api_uptime, list_apis, list_recent_incidents. The verbs (check, get, list) are used predictably to distinguish action types, and nouns are descriptive.
Five tools is an ideal size for an API monitoring server. Each tool covers a distinct monitoring need without redundancy or bloat, and the scope is tightly focused on status and reliability queries.
The tool surface fully covers the core domain: discovering tracked APIs, checking current status individually or in bulk, retrieving historical uptime, and listing recent incidents. No essential monitoring operation appears to be missing for common agent workflows.