Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the full burden and delivers substantial behavioral detail: the return value (iCalendar UID), timezone interpretation for ISO 8601 values, the non-obvious end_date-inclusive semantics for all-day events, the constraint that the first occurrence must match the RRULE, and DST behavior. It stops short of disclosing error/failure behavior and idempotency, which keeps it from a 5.

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 ~130-word paragraph ordered from the core action to return value, time semantics, all-day handling, and recurrence rules. Every sentence carries high-value information, the RRULE examples are concrete, and the subtle end_date-inclusive and DST notes earn their place. No filler or repetition.

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 tool with 7 parameters, 0% schema coverage, and no annotations, the description covers the hardest parts—timezone, all-day, recurrence, and return value (with an output schema also present). The remaining gaps are calendar_name resolution (must the agent derive it from list_calendars?) and expected error behavior on invalid input. These are material for a create operation but secondary to the semantics already disclosed.

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 0%, so the description must compensate. It richly documents the genuinely ambiguous parameters: start_time/end_time (ISO 8601, timezone handling, date-only convention) and recurrence (exact RRULE format with three concrete examples plus constraint). Self-evident fields like location and description need no elaboration. However, calendar_name—a required parameter—is never explained as display name vs. ID or connected to list_calendars.

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 opens with a specific verb+resource: 'Publish a new event to an iCloud calendar.' The creation intent is unmistakable and clearly distinguishes this tool from siblings like get_event, update_event, delete_event, and list_events. An agent can differentiate it without inspecting schemas.

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?

While it never explicitly names alternatives or says 'use this instead of update_event,' it gives clear operational context: date-only values signal all-day events, and recurrence requires an RRULE whose first occurrence must match the rule. The conditional guidance ('To make it repeat...', 'Give date-only values...') effectively tells the agent how to shape the call for each scenario. It lacks explicit exclusions, so not a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that cancellations are not sent to attendees, explains the effect of omitting occurrence (deleting the whole series), and instructs to check warnings in the result. This goes beyond typical expectations for a delete tool.

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 concise yet comprehensive, front-loading the core action and then providing conditional details in a logical order. Every sentence adds value, with no redundancy or fluff.

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 complexity of handling recurring events and the existence of an output schema, the description covers all necessary information: deletion scope, recurrence handling, cancellation behavior, and result inspection. Nothing critical is 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?

Schema description coverage is 0%, so the description must compensate. It explicitly explains the meaning and usage of occurrence and and_following, which are the non-obvious parameters. Event_id and calendar_name are self-explanatory from their names and the description's context. The description effectively adds meaning to all parameters.

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 ('Delete') and resource ('event'), and clearly distinguishes deletion of a single event from deletion of a recurring series. It differentiates from siblings like update_event and list_events by focusing on deletion semantics and mentioning list_events for obtaining recurrence IDs.

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 explicit guidance on when to use the occurrence and and_following parameters, and explains the behavior for recurring events. It does not explicitly list when not to use this tool versus alternatives, but the context is clear from the tool name and the description, so it is not misleading.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. 'Fetch' signals a read-only operation, and the description goes further by explaining exactly what a repeating event returns: first occurrence, recurrence rule, excluded occurrences, and modified occurrences. This is valuable context beyond the schema.

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 two tightly written sentences. The action is front-loaded, and the second sentence adds high-value recurrence behavior without any 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?

This is a simple read tool and an output schema exists, so return values are covered. The recurrence behavior is a strong addition. However, the under-explained required calendar_name parameter leaves a meaningful gap in the input contract, making the description incomplete for fully correct invocation.

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 0%, so the description must explain the parameters. It addresses event_id but completely omits calendar_name, which is required and has no documented meaning. An agent cannot tell why calendar_name is needed or how it relates to event_id from this description.

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 uses a specific verb and resource ('Fetch one event by its event_id') and clearly distinguishes this from list_events by emphasizing it returns a single event. The added detail about repeating events gives additional precision and makes the tool's scope unmistakable.

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 clearly implies this tool is for retrieving a single known event by ID, which is a clear usage context. It does not explicitly contrast with list_events or state when not to use it, but the one-by-ID framing is enough for an agent to route correctly most of the time.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries the full burden. It clarifies the scope ('available to the account') and the output content, but since it is a list operation with no side effects, the read-only nature is strongly implied by the name. It does not explicitly state auth requirements or whether the output is a flat array, which an output schema may cover.

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 tight sentences with no filler. The core purpose is front-loaded, and the usage guidance is concise and actionable.

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 zero-parameter discovery tool, the description is complete. It states what is returned, the scope, and how the result feeds into sibling tools. The output schema is present, so detailed return structure does not need to be repeated.

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 has zero parameters, so the description does not need to explain parameter behavior. It adds value by telling the agent what the output will be useful for, specifically the `calendar_name` consumed by event tools.

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 action ('List the iCloud calendars available to the account') and resource, plus the returned data ('names and CalDAV URLs'). It clearly differentiates this from the sibling event-focused tools by emphasizing calendar discovery rather than event operations.

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 explicitly tells the agent when to use this tool: to discover the exact `calendar_name` expected by `create_event` and `list_events`. This gives a concrete, actionable purpose and names the dependent sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It reveals the default 30-day range, expansion of recurring events, and the 400-day limit. These are meaningful traits beyond the schema, though it omits details like date format or pagination.

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, zero filler, with the primary action stated first. Each sentence adds a distinct piece of information: purpose, default behavior, and a constraint.

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 an output schema exists and annotations are absent, the description covers the essential operational aspects: what the tool does, default range, recurrence expansion, and rejection of long ranges. The main gap is parameter format guidance, but overall the context is largely sufficient.

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 0%, so the description must explain parameters. It mentions 'time range' and defaults but never maps start_date/end_date to the range bounds or explains calendar_name's role. The constraint on long ranges is behavioral, not parameter-specific.

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 the action ('Fetch events'), the resource ('iCloud calendar'), and the scope ('within a time range'). It is immediately distinguishable from siblings like create_event, get_event, and delete_event.

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 gives helpful context (time range, default period, rejection of long ranges) but never explicitly tells the agent when to choose this over get_event or list_calendars. The intended use case is implied but not contrasted with alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and delivers extensively: partial-update semantics, empty-string clearing, duration preservation when only start_time changes, per-occurrence vs whole-series editing, RRULE replacement/clearing, series-move effects on exceptions with removed_exceptions, unsupported and_following, and no invitations. This is exemplary behavioral disclosure.

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?

Densely packed and logically ordered, starting with the basic semantics and then handling recurrence edge cases, limitations, and reminders. Every sentence adds behavioral nuance needed for correct invocation, with no filler or repetition.

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?

Coverage is strong for the hard parts: recurrence scoping, series moves, exception counting, and the unsupported and_following case, and it points to warnings in the result. Minor gaps exist around end_time semantics, datetime format, and not-found behavior, but these are small given the complexity and the presence of an output schema.

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 0%, so the description must compensate. It explains the nuanced semantics of start_time (moves event, keeps duration), occurrence (recurrence_id scope), recurrence (RRULE vs empty string), and clearing description/location. Only end_time and event_title lack explicit mention, but their meanings are obvious from names.

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 'Change an existing event' with a specific verb and resource. The contrast with siblings (create/delete/get/list) is clear from 'existing' and the subsequent modification semantics, so an agent can distinguish it without opening schemas.

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 names delete_event(..., and_following=true) as the alternative for unsupported 'this and all following' changes and points to list_events for retrieving recurrence_id. It does not explicitly cover when to use create_event vs update_event, but the 'existing event' qualifier makes that implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.