Secret Santa Raffle

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the write nature is already known. The description adds genuinely non-redundant behavior: the draw is created immediately and cannot be modified from this server afterwards, plus a note that the first participant becomes organizer and that the result carries a draw id and share code.

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?

Front-loads the core purpose, then requirements, then lifecycle constraint, then the two follow-up paths. Every sentence carries information, though the long brand/alias enumeration in the opening does add some visual weight.

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, the description need not detail return values, yet it briefly previews the draw id and share code. Combined with the irreversibility warning, required-input summary, and sibling routing, an agent has everything needed 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 description coverage is 100%, so the baseline is 3. The description reinforces which arguments are required versus optional, but most of that detail (organizer ordering, minItems 3, locale/brand mapping, optional budget and message) is already spelled out in the schema descriptions, so it adds little new meaning.

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 and resource ("Creates a Secret Santa / gift exchange draw") with concrete mechanics (random pairing, exclusion rules honored). It is immediately distinguishable from the invitation-focused siblings, which are not creation tools.

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 separates required inputs (date, 3+ participants) from optional ones and explains the follow-up routing to send_invitations_email or get_group_share_message. It does not name a condition under which you would choose a different creation path, but none exists, so the gap is minor.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds the key behavioral fact that nothing is actually sent and that output must be copied manually into a chat, which the annotations do not convey. It stops short of describing the message format or length.

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 tight sentences, front-loaded with the action and artefact, followed by localization scope and the sibling comparison. Every clause 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?

An output schema exists, so return-value detail is not needed. With annotations covering the safety profile and the description covering purpose, alternative and the no-side-effect guarantee, an agent has enough to call this correctly. Minor gap: drawName's meaning is left entirely to inference.

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 67% and the locale parameter already carries a very rich description (BCP 47 tags, brand mapping, precedence rules). The description restates the localization/brand behaviour but adds little syntax-level detail, and drawName has no schema description at all while the description never mentions it. Baseline 3 is appropriate.

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 and artefact: 'Generates a ready-to-paste WhatsApp/Telegram message announcing a freshly created draw.' It also distinguishes itself from the sibling send_invitations_email by framing itself as the no-email alternative, so an agent can tell the two apart without opening either 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 names the alternative and the selecting condition: 'It is the alternative to send_invitations_email for sharing without emails: nothing is sent.' The when/when-not is unambiguous.

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?

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely new context beyond them: the send is immediate and irreversible, and a draw admits only one bulk send. That irreversibility detail is exactly the kind of operational constraint annotations cannot express.

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?

Four short sentences, front-loaded with the action and its scope, then the irreversibility constraint, then the inputs. Every sentence carries information; 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?

An output schema exists, so return values need not be described. The description covers scope, prerequisites, and the one-shot irreversible nature of the send, leaving only edge cases (error behavior, what happens on a second send) unstated.

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 67%, with locale and shareCode richly documented inline. The description adds provenance meaning for the two required parameters — that drawId and shareCode come from create_draw — which the schema does not state for drawId. Locale semantics are left entirely to the schema, so it is not a full 5.

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 ('Sends the email invitation to all participants of a draw') and scopes it to a draw created in this same conversation. It is clearly distinguishable from create_draw and get_group_share_message, one of which produces the identifiers this tool consumes.

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 the prerequisite ('drawId and shareCode returned by create_draw') and the context constraint ('created in this same conversation'). It does not, however, name an alternative (e.g. get_group_share_message) or state when not to call it, so it stops short of full routing guidance.

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