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

With no annotations at all, the description carries the full burden, and it does disclose the single most consequential behavior: attendees are silently added unless send_invitations is true. That is genuinely useful side-effect disclosure, but it says nothing about permissions/scopes required, what happens on duplicate or conflicting events, or what the tool returns on success.

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 short sentences, no filler, and the highest-risk behavior is placed where it will be read. Every sentence carries a distinct instruction or disclosure.

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 an 11-parameter write tool with no annotations and no output schema, the description covers the interaction protocol and the invitation side effect but omits conflict handling, required permissions, and confirmation of what is returned. It is adequate to call the tool correctly but not complete for a mutation of this surface area.

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 64%, so the schema already explains start format, time_zone, calendar, days, and duration defaults. The description adds real semantic value for send_invitations and attendees by explaining the silent-add default, which the schema only hints at. The remaining parameters (title, location, description, all_day) are self-evident, so the baseline of 3 fits.

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 and resource ("Create an event"), which cleanly separates it from the read-oriented siblings list_calendars and find_calendar_events. It does not explicitly contrast itself with update_calendar_event, but the create/update distinction is obvious enough that an agent can route without ambiguity.

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?

It gives one concrete procedural rule ("Confirm title, time and time zone with the user first") and a conditional for invitations, which is real usage guidance rather than none. However, it never states when to use this versus update_calendar_event or what to do when an event may already exist, leaving the sibling comparison to inference.

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 does disclose two meaningful behaviors: the default 30-day window and that recurring events are expanded into individual occurrences (which affects result volume). It is silent on result ordering, pagination behavior, whether all calendars are searched when none is specified, and any permission requirements.

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, no filler, and the core scope plus default behavior are front-loaded before the recurrence note.

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 5-parameter read tool with no annotations, no output schema, and 40% schema coverage, the description is adequate but leaves real gaps: which calendar is searched by default, how results are ordered, and whether limit truncates occurrences or base events. These matter for 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 coverage is only 40%, and the description compensates for part of it by explaining that text is an optional match filter and that the two time bounds define the search window (with a default). It says nothing about the 'calendar' parameter's semantics (default calendar vs. all calendars) or how 'limit' interacts with recurrence expansion, leaving two of five parameters unexplained in prose.

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 (find) and resource (calendar events) plus the temporal scope, which implicitly separates it from the create/update/list_calendars siblings. It never explicitly contrasts itself with those siblings, but the read/search nature is 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 default window ('the next 30 days') and the optional text filter imply the intended use case, but there is no explicit when-to-use or when-not-to-use guidance and no pointer to a sibling for other needs (e.g., listing calendars first to obtain a calendar identifier).

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 must carry the behavioral burden. It does disclose the visibility scope ("can see") and that the response marks the default calendar, which implies a read-only operation, but it says nothing about ordering, whether hidden/subscribed calendars are included, or permission/auth requirements for a listing call.

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 compact sentence with zero filler; the scope qualifier and the default-flag detail are front-loaded and each earns its place.

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 read with no output schema and no annotations, the description covers what the tool returns (visible calendars plus the default marker). Only minor gaps remain, such as result ordering or whether the output is meant to feed the sibling event tools.

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 the baseline is 4 and there is no parameter meaning left to compensate for. The description correctly implies no input is needed.

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?

"List the calendars this account can see, with which is the default" names a specific verb (List) and resource (calendars) and scopes it to the account's visibility, which cleanly separates it from the event-oriented siblings. It does not explicitly reference those siblings, but the resource distinction is unambiguous.

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 only implied: an agent can infer this is the discovery step before calling find_calendar_events or create_calendar_event, but the description never says when to use it, when not to, or that its output feeds the other tools. No exclusions or prerequisites are stated.

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?

No annotations are supplied, so the description carries the behavioral burden. It usefully discloses that this is a partial update ('only the fields to change') rather than a full replacement, but says nothing about permissions, reversibility, attendee notification side effects, or rate limits.

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 single sentence is front-loaded with the purpose and then gives the key calling instruction; no words are wasted. Its brevity is appropriate, though it contributes to the missing behavioral detail noted elsewhere.

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 12-parameter mutation with no annotations and no output schema, the description covers the core invocation but omits side effects and permissions. It is minimally adequate when combined with the 58% schema descriptions, but not fully complete for the tool's complexity.

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 58%, so several parameters are undocumented in the schema. The description adds the partial-update rule for optional fields and names event_id, but does not explain semantics for title, all_day, location, description, or event_id beyond what is obvious.

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 mutation ('Change') on a specific resource ('an existing event'), and 'existing' distinguishes it from create_calendar_event. An agent can identify this as an update operation 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?

It states the precondition ('existing event') and the invocation pattern ('give event_id and only the fields to change'), making partial updates clear. It does not name alternatives such as create_calendar_event for new events or find_calendar_events for locating an event, so it falls short of a full when-to-use guide.

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