Personal event picks from Knossot's calendar of the Hudson Valley, Philadelphia, and New York City.
Scored across 3 tools
The three tools serve clearly distinct purposes: account/usage status, reference data for regions and categories, and the core recommendation action. There is no overlap that would cause an agent to misselect a tool.
All tool names follow a consistent verb_noun snake_case pattern: get_usage, list_regions, recommend_events. This is predictable and readable.
Three tools are well-scoped for a focused recommendation service. Each tool earns its place, and the count is within the typical 3-15 range without being excessive or thin.
The tool surface covers the full read-only lifecycle: checking usage limits, discovering regions and categories, and obtaining personalized event recommendations. No obvious gaps or dead ends exist for the stated service purpose.
This key's spending limit, whether the free weekly run is still available, and the credit balance.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| key | Yes | |
| credits | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the specific data reported (spending limit, weekly free run status, credit balance), which is useful behavioral context, but since an output schema exists these returns are partly documented elsewhere. No mention of rate limits, auth requirements, or refresh behavior.
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 no filler, and the three reported values are listed together. It reads as a sentence fragment rather than a full statement, but nothing needs to be cut.
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?
With zero parameters, a full output schema, and annotations covering the read-only/closed-world profile, the description only needs to orient the agent, which it does. The remaining gaps (when to check, whether the balance is cached or live) are minor for a simple status-read tool.
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 tool takes zero parameters, so per the rubric the baseline is 4. The description correctly implies the key is inferred from context rather than passed in, and no parameter information is needed or missing.
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 the resource (this key's usage/credits) and enumerates the specific outputs: spending limit, free weekly run availability, and credit balance. It is clear what the tool reports, though the verb is only implied rather than stated. Sibling tools (list_regions, recommend_events) are unrelated domains, so no differentiation is required.
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?
Usage is implied by the content — an agent would call this to check quota/credit status — but there is no explicit when-to-use statement or exclusion. No alternatives are named, though the siblings are unrelated enough that routing ambiguity is minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The four regions with their towns, the category ids recommend_events accepts, and the run limits. Needs no key.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| picks | Yes | |
| window | Yes | |
| regions | Yes | |
| categories | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a genuinely useful behavioral fact beyond the annotations: 'Needs no key', meaning no authentication is required. It does not go further into caching or freshness of the reference data.
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 sentence that front-loads the returned content and ends with the auth fact. Every clause earns its place and nothing is padded.
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?
With an output schema present, the description need not enumerate return shapes, and the annotations cover safety. It states what is returned, that no key is needed, and hints at its role for recommend_events, leaving only the explicit when-to-use guidance missing.
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?
This is a zero-parameter tool with an empty object schema, so the baseline of 4 applies. The description appropriately adds no parameter detail because there are no parameters to describe.
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 the concrete contents returned: the four regions with towns, the category ids recommend_events accepts, and the run limits. It implicitly differentiates from siblings by linking to recommend_events, though it never states a verb like 'list' or 'retrieve'.
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?
Usage is implied rather than stated: an agent can infer this is a reference lookup for category ids and run limits before calling recommend_events. There is no explicit when-to-use, when-not-to-use, or comparison against get_usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Personal picks from the published Knossot calendar for a brief, in one region and a window of up to 14 days. Up to 3 picks on the free weekly run, up to 5 on credits ($0.075 per run, charged only when picks come back). Repeating the same arguments in the same ten-minute window replays the earlier picks free; pass a new idempotency_key to ask again.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | Eastern date; default from + 6; window at most 14 days, within 60 days. | |
| free | No | ||
| from | No | Eastern date; default today. | |
| brief | Yes | Never stored. | |
| region | Yes | ||
| category | No | ||
| max_picks | No | ||
| exclude_keys | No | ||
| idempotency_key | No | Optional; one key per distinct run. |
| Name | Required | Description |
|---|---|---|
| run | Yes | |
| picks | Yes | |
| replayed | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations: discloses cost ($0.075 per run, charged only when picks return), the free weekly cap vs. credit cap, and the ten-minute replay/caching window that explains the idempotentHint. It also gives the reader the reason readOnlyHint=false (credit side effect) without contradicting it.
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 dense sentences, front-loaded with purpose before pricing and caching details. Each sentence carries real information (scope, economics, idempotency). Slightly packed but no 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?
With an output schema present, return values needn't be described. For a 9-parameter billing-aware tool, the description covers the essential purpose, cost model, and caching behavior, leaving only minor per-parameter detail gaps that the schema partially fills.
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 44% (below 50%), so the description should compensate, and it partially does by tying the 14-day window to from/to and the pick counts to max_picks/free. But it adds nothing for region, brief, category, or exclude_keys semantics. Partial compensation warrants a 3.
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?
States a specific verb+resource: 'Personal picks from the published Knossot calendar for a brief, in one region and a window of up to 14 days.' An agent immediately knows this returns curated event recommendations scoped by brief/region/date. Sibling differentiation (get_usage, list_regions) is only implicit, so it stops short of a 5.
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?
Provides meaningful context for *how* the tool behaves (free weekly run vs. credits, charge only when picks return), which indirectly tells the agent when to call it. However it never states when-not-to-use it or names an alternative among get_usage/list_regions, so usage routing is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_usagelist_regionsrecommend_eventsLive New York events, shows, classes, tours, markets, music, theater, comedy, art and nightlife
Real local places, events, and movie/TV picks, plus decision-maker games (wheel, dice, bracket).
Live event discovery: concerts, club nights, art, comedy, and festivals across 14 cities.
Local US events: trivia, libraries, markets and gigs, with VenuNite links and ticket handoffs.
Add one secure layer between your agents and this server.
