discover_eventsUse to rank cited events in the latest completed edition by probable, rare, or overweighted mode. Keep research priors separate from measured current-edition counts. Do not describe the result as a forecast or a probability that an event occurred.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | ||
| limit | No | ||
| category | No | Only return replacements in this category. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly and idempotent annotations, the description discloses that the tool operates on the latest completed edition and uses measured current-edition counts rather than prior expectations. The explicit warning not to describe results as a forecast or probability adds important interpretive context for the agent.
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 sentences with no wasted words. The core purpose is front-loaded in the first sentence, and the two subsequent sentences provide essential constraints and cautions. Every sentence adds value.
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 key scope and behavioral constraints, and the schema documents parameters. However, since there is no output schema, the exact return format is not described beyond implying a ranked list. For a tool of this simplicity, this is a minor gap.
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 description coverage is only 33%, but the description connects the required 'mode' parameter to the ranking behavior, giving it meaning beyond the bare enum. The 'limit' parameter is self-explanatory given schema bounds, and 'category' already has a schema description. The description partially compensates for the low coverage on the most important parameter.
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 explicitly states the action ('rank'), the target resource ('cited events in the latest completed edition'), and the operating modes ('probable, rare, or overweighted'). This clearly distinguishes the tool from siblings like read_latest_edition or score_headline, which serve different purposes.
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 opening 'Use to rank...' provides a clear when-to-use instruction. It does not explicitly name alternatives or exclusions, but the specific task and scope make it obvious when this tool is appropriate. The added caution about research priors versus measured counts also guides correct usage context.
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.
The watch and edition tools are clearly distinct, but get_context and score_headline overlap heavily—both accept a headline, share the referenceContext parameter, and disclose withheld/conflicting info—and get_brief vs read_latest_edition both serve 'what's the latest news' requests. The verbose 'do not use for' guardrails in the descriptions help, but they also signal that the boundaries are not naturally obvious.
All names follow snake_case verb_noun, with predictable patterns: list_* for collections, create/update/acknowledge for watch mutations, read_* for editions. Minor inconsistency exists between get_brief and read_latest_edition (both fetch news content) and between get_membership and list_watches (both return list-like info), but the overall scheme is readable and consistent.
14 tools sits within the typical well-scoped band, and each tool appears to serve a real product feature. The surface is slightly broad for a 'news' server, spanning saved-watch management, edition reading/export, headline analysis, and membership/checkout, which makes it heavier than a focused news reader.
Edition access (list/read/export) and the analysis workflow (score/context/discover) are well covered, but the watch lifecycle has no delete_watch, leaving agents unable to remove saved watches—a real dead end. There is also no story-level read or search tool, though the descriptions explicitly scope that out.