Find open times and book a free Cicero Learning consultation.
Scored across 2 tools
The two tools have clearly distinct purposes: one lists availability, the other books a slot. Their descriptions explicitly reference each other, leaving no ambiguity about which to use.
Both names use snake_case and follow a verb_noun pattern, but they mix verb types ('book' vs 'list') for complementary operations. This is readable and consistent enough, with only a minor deviation from perfect parallel structure.
With only two tools, the surface feels thin for a booking system. While each tool earns its place, the scope is borderline limited, lacking operations like rescheduling or cancellation despite mentioning a manage URL.
The server covers availability listing and booking but omits key lifecycle operations: there is no tool to reschedule or cancel a booking even though the confirmation includes a manage URL. Major gaps force guests to use an external interface for common actions.
Book a Cicero consultation. Use a startIso/endIso pair returned by list_consult_availability. Returns a confirmation with a manage URL the guest can use to reschedule or cancel.
| Name | Required | Description | Default |
|---|---|---|---|
| note | Yes | Why the guest is booking / what they'd like to discuss (required). | |
| endIso | Yes | Slot end (UTC ISO-8601) from availability. | |
| startIso | Yes | Slot start (UTC ISO-8601) from availability. | |
| customerName | Yes | The guest's full name. | |
| customerEmail | Yes | The guest's email address. | |
| customerPhone | No | Optional E.164 mobile (e.g. +14155550123) for SMS reminders. | |
| eventTypeSlug | Yes | The event type, e.g. "cicero-consult". | |
| customerTimezone | Yes | The guest's IANA timezone, e.g. "America/New_York". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses the outcome (a confirmation plus a manage URL for reschedule/cancel), but is silent on permissions/auth, conflict or failure handling, and whether notifications are sent to the guest. Genuine context is added, yet key mutation-side traits are missing.
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, purpose front-loaded, each carrying distinct information: what it does, the required input source, and what comes back. No filler or redundancy.
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 mutation tool with no annotations and no output schema, the description covers the essential invocation prerequisite and the returned confirmation/manage URL. It leaves error and conflict behavior unstated, but an agent has enough to call it correctly.
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%, so the baseline is 3. The description goes beyond the schema by explaining the provenance constraint on startIso/endIso (they must come from list_consult_availability), which the parameter descriptions only allude to. It does not explain eventTypeSlug or tz choices further.
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 (Book) and resource (a Cicero consultation), which is immediately distinguishable from the sibling list_consult_availability that only reads slots. An agent knows exactly what this tool accomplishes without opening the schema.
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?
Explicitly ties invocation to a prerequisite: 'Use a startIso/endIso pair returned by list_consult_availability.' That routes the agent to the correct upstream call. It does not state any when-not-to-use condition (e.g., double-booking, unavailability), so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List open time slots for a Cicero consultation event type over a date range. Returns UTC ISO-8601 start/end instants the guest can book.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ISO-8601 end of the search window. Defaults to 30 days after "from". Windows wider than 62 days are clamped. | |
| days | No | Alternative to "to": number of days after "from" to search (default 30). | |
| from | No | ISO-8601 start of the search window. Defaults to now. | |
| eventTypeSlug | Yes | The event type to book, e.g. "cicero-consult". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses the return format ('UTC ISO-8601 start/end instants'), which is useful since no output schema exists. However, it does not mention authentication requirements, rate limits, or explicitly confirm the operation is read-only/non-destructive.
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 tightly written sentences with zero waste. The primary purpose is front-loaded, and the return format follows as a useful secondary detail.
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 list tool with a fully described schema but no output schema, the description supplies the critical return-format information. The main gap is the absence of guidance on when to choose this tool over the sibling 'book_consult'.
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 schema fully documents all four parameters including defaults and clamping behavior. The description adds only the phrase 'over a date range', which does not meaningfully extend parameter semantics beyond 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 states a specific verb ('List') and resource ('open time slots') scoped to a 'Cicero consultation event type over a date range', which is clear and distinguishable from a booking tool. However, it does not explicitly name the sibling 'book_consult' or contrast itself with it, leaving some ambiguity for an agent deciding between listing and booking.
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 provides no explicit when-to-use guidance or alternatives. It implies availability checking precedes booking but never states that 'book_consult' should be used for actual reservations, nor does it list exclusions or prerequisites.
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.
book_consultlist_consult_availabilityFree scheduling your agent can book through: live availability, booking, verification, cancel.
Find and book verified 1-on-1 online tutors: search by subject, price and rating, then book.
Check availability and book a free consult for Bay Area senior/disabled meal-prep delivery
AI-native scheduling and booking: check availability, book meetings, share links.
Add one secure layer between your agents and this server.
