get_squawk_sessionsLive events Helious transcribed in the last week (Fed pressers, briefings), one entry per event.
| Name | Required | Description | Default |
|---|---|---|---|
| fresh | No | Set true to ask for the live view of this one call, for 5 credits, where the connected account otherwise receives it an hour behind. Accepted and free where the account is already live. No effect without a key. | |
| hours | No | How many hours back, up to 168. |
Changes observed during successful MCP inspections.
Input schema / properties / fresh / descriptionPrevious value: -"Not on Pro or Ultimate? Set this to true and this one call answers live for 5 credits. Left out, Free, Squawk and Starter get the answer an hour behind for 1 credit. Pro and Ultimate are live already, so it costs nothing extra there. No effect without a key."New value: +"Set true to ask for the live view of this one call, for 5 credits, where the connected account otherwise receives it an hour behind. Accepted and free where the account is already live. No effect without a key."Input schema / properties / freshAdded value: +{
+ "description": "Not on Pro or Ultimate? Set this to true and this one call answers live for 5 credits. Left out, Free, Squawk and Starter get the answer an hour behind for 1 credit. Pro and Ultimate are live already, so it costs nothing extra there. No effect without a key.",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds only the one-week retention window and one-entry-per-event shape. It does not disclose the credit-charging live-view path or the one-hour lag that the schema hints at, which is exactly the kind of behavioral detail worth surfacing here.
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?
A single tight sentence with the resource and scope front-loaded and no filler. It is efficient, though the brevity contributes to the missing usage and parameter context.
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?
No output schema exists and both parameters are optional, so the description needn't explain return values in depth; annotations plus the 100%-covered schema carry safety and parameter detail. The remaining gap is that an agent gets no sense of what an entry contains or how the default week-long window relates to `hours`.
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 100%, so the baseline is 3. The phrase "last week" usefully corroborates the default window implied by the `hours` parameter (up to 168), but the description says nothing about `fresh`, the credits cost, or key requirements — all of which live only in the schema.
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 names a specific resource (live events transcribed by Helious) with concrete examples (Fed pressers, briefings) and states the return granularity (one entry per event). It is clearly not the same as rate-curve or calendar siblings. It stops short of explicitly distinguishing itself from get_feed, which could plausibly overlap.
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?
"In the last week" implies a recency scope, but there is no explicit when-to-use, no when-not, and no named alternative among the 24 siblings. An agent must infer that this is for recent transcribed audio/video events rather than market data feeds.
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.