Recorded incidents for a hosting or API provider over a window, kept after the provider’s own status page dropped them.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| provider | No | Provider slug, e.g. cloudflare, openai, github. Omit for every provider. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It reveals a notable data-retention behavior (incidents kept even after the status page drops them) and implies a read-only operation via 'Recorded'. However, it does not describe response shape, pagination, or any prerequisites, leaving some behavioral ambiguity.
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 a single sentence that immediately conveys the core purpose and a key differentiator. Every word contributes value, with no redundancy or filler.
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?
Given the tool's low complexity (two optional parameters, no output schema), the description is reasonably complete for initial selection. However, without an output schema, it leaves the return format unspecified—only mentioning 'Recorded incidents'—and does not address potential edge cases like empty results or provider limitations. More detail on the output structure 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 schema provides descriptions for 'provider' but not for 'days' (50% coverage). The description hints at the meaning of 'days' through 'over a window' and clarifies the provider scope as 'hosting or API provider', but it does not name parameters explicitly or explain the day window format. This partially compensates for the schema gap without fully resolving it.
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 that the tool provides recorded incidents for a hosting/API provider over a time window. Although it uses a noun phrase rather than an explicit verb like 'get' or 'list', it effectively communicates the action and scope, and the detail about incidents outliving the provider's status page distinguishes it from a live status checker.
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 implies usage for historical incident data ('kept after the provider’s own status page dropped them') but does not explicitly mention when to use this tool versus alternatives like provider_incidents. There is no direct comparison to sibling tools or exclusions, so usage context is present but not fully explicit.
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 overlap significantly: check_package, check_before_install, check_stack, and audit_manifest all inspect dependencies, while check_provider and provider_incidents both return incident data. Descriptions help somewhat, but the boundaries between these tools are unclear and could easily cause misselection.
Tool names follow no consistent pattern: some start with verbs (check_*, list_*, search_*), others are noun phrases (advisory_severity, domain_risk, provider_incidents), and one is a clause (who_can_publish). The mixed conventions reduce predictability and make it harder to infer tool behavior from the name.
With 31 tools, this is well above the 25-tool threshold for a single server, making the surface feel heavy and difficult to navigate. Even given the broad domain (packages, providers, models, registries), many tools could be consolidated or grouped more tightly.
The server provides extensive read coverage for packages, providers, models, and registries, but there are notable gaps such as no watchlist removal or model comparison, and some tools appear redundant rather than completing a lifecycle. Overall, it is broadly useful but not fully complete for its stated purpose.