Voidmail (hosted)

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds a genuine non-structured disclosure — that sender and subject are untrusted data — which is a real prompt-injection warning, though it says nothing about pagination or return shape.

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 the scope stated first and the security caveat second; nothing is wasted. It is arguably over-terse for a tool whose schema fields are undocumented, but every sentence 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?

With no output schema and 0% parameter documentation, the description should explain the pagination model and return format, but it does neither. It also omits any guidance on choosing this tool over voidmail_read_email.

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% for three parameters, so the description carries the burden and largely fails: it hints at the limit ('up to ten messages') but never explains offset for paging or what unreadOnly filters.

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?

Specific verb (List) plus resource (messages in the authenticated mailbox), with a stated scope cap of ten. It is implicitly distinct from voidmail_read_email, but the description never names that sibling or explains the list-vs-read distinction.

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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as voidmail_read_email for fetching a single message. The agent must infer the routing from the name alone.

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 give the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds real value on top: it discloses the mutation ('mark it read') and warns that message text is untrusted data, plus content limitations (attachments/HTML excluded). It does not mention auth needs or rate limits, but the untrusted-data warning is a useful addition beyond structured fields.

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 the core action front-loaded and a second sentence covering the security/content caveats. No wasted words.

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 single-message read tool with no output schema and no annotations on return format, the description adequately conveys what is returned ('bounded plain-text message', attachments/HTML excluded). Minor gaps remain around error behavior and how the ID is obtained.

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?

One parameter with 0% schema description coverage, and the description never references emailId or its format. The parameter name is self-evident, so the gap is mild, but the description fails to compensate for the missing schema documentation.

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 (read) and resource (one plain-text message) with clear scope ('bounded', 'one'). An agent can distinguish this from voidmail_list_inbox without opening the schema, though no sibling is named explicitly.

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 side effect ('mark it read') and content scope imply when to use it, but there is no explicit when-to-use guidance, no prerequisites, and no routing to alternatives like list_inbox for finding IDs first.

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 readOnly/idempotent/non-destructive/closed-world, so the bar is lower; the description still adds real context by asserting the limits are "static" and that the call neither reserves capacity nor proves delivery. That rules out side effects the agent might otherwise assume from a limits endpoint. It stops short of describing freshness or what the limits are keyed to.

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 short sentences, zero waste, with the positive statement of purpose front-loaded and the caveat immediately after. Ideal size for a no-arg read tool.

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?

No output schema exists, yet the description does not indicate what the returned limits contain (per-domain, per-day, account-wide?) or their units. For a zero-param read tool with full annotation coverage the description is nearly sufficient, but that single return-shape gap keeps it off a 5.

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; there is nothing for the description to disambiguate beyond the empty 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 gives a specific verb and resource ("Read static sending limits"), and the qualifier "static" plus the negative claims distinguish it from the mutation/verification siblings (voidmail_send_once, voidmail_send_status). It does not name an alternative explicitly, so an agent must infer the routing from the negations.

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?

"This does not reserve capacity or prove delivery" is explicit when-not guidance: it tells the agent not to treat this as a pre-send reservation or a delivery-verification step, which is exactly the confusion the sibling send tools would create. No positive statement of when to call it (e.g., before composing a campaign), but the exclusion is clear context.

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?

The annotations already declare this as a non-readonly, non-idempotent, open-world mutation, so the bar is lower; the description still adds two things the annotations cannot: that the caller owns the operation ID for safe retries, and that a successful response means acceptance, not delivery. That second point is genuinely useful behavioral context for a send 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?

Two sentences, zero filler, and the core action is front-loaded before the retry and delivery caveats. Every clause carries information an agent needs.

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 four-parameter send tool with no output schema, the description covers the action, the idempotency-key contract, and the meaning of success. It leaves the path to actually confirm delivery unstated, which the voidmail_send_status sibling presumably covers.

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 0%, so the description must carry the load for four required params. It adds real meaning for operationId ('caller-saved', i.e. caller-generated and persisted) and identifies text as plain-text-only, but says nothing about `to` or `subject` beyond what the schema 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?

The description states a specific verb and resource ('Submit one plain-text message') and scopes it to a single send, which distinguishes it from voidmail_send_status and voidmail_sending_limits without naming them. It is clear, though it never explicitly contrasts itself with its siblings.

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?

'Never retry with a new ID after uncertainty' is a concrete invocation rule for the retry path, and 'acceptance is not delivery' hints that delivery must be verified elsewhere. However, it never names voidmail_send_status or any other tool as the way to confirm delivery, so the routing guidance is only implied.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. 'Without dispatching mail' largely restates readOnlyHint and adds no new behavioral context such as what status output is produced, how long the operation ID stays valid, or failure modes.

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 short sentence with no filler, and the non-dispatching constraint is placed where it reads as the key differentiator. It is efficient, though the terseness borders on cryptic rather than front-loading the actual purpose.

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?

There is no output schema and the description says nothing about what is returned — status values, error states, or whether it blocks until completion. For a status-lookup tool with a single undocumented parameter, the description leaves the agent guessing about the response.

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 schema only supplies a pattern and no meaning. The description partially compensates by characterizing the parameter as a 'durable operation ID' that persists from a prior call, but does not explain the format beyond the regex or where the ID comes from.

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 verb 'look up' plus the resource 'operation ID' gives a rough sense of a status/result retrieval, and 'without dispatching mail' implicitly distinguishes it from voidmail_send_once. However, it never plainly states that it returns the status of a previously dispatched send, and 'the same durable operation ID' presupposes context the agent may not have.

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 phrase 'without dispatching mail' hints at the contrast with voidmail_send_once (dispatch vs. not), which is implied usage guidance. It does not explicitly say 'use this to poll the result of a send_once call' nor state any preconditions, so the routing signal is only inferable.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is largely covered. The description adds genuinely useful negative disclosure beyond those hints: it never creates a mailbox and never returns credentials, which pre-empts the most likely misconception about a tool named 'setup'. It does not, however, describe what the check actually reports.

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 short sentences with no filler, and the negative constraint is placed immediately after the action so it is read before invocation. The first sentence is slightly convoluted ('or show the owner-controlled setup path'), which costs a point.

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 no output schema, the description bears responsibility for indicating what the call returns, and it does not — an agent cannot tell whether to expect a status object, a URL, or prose instructions. For a zero-param read-only tool this is a modest gap rather than a fatal one, so 3 is appropriate.

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, which is the baseline-4 case; there is no parameter surface for the description to explain. Nothing is misrepresented or omitted.

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 verb ('Check') and rough resources ('a configured inbox', 'the owner-controlled setup path'), so it is identifiable as a configuration/diagnostic tool. However, 'check a configured inbox' does not say what is checked (config validity? connectivity? readiness?) and 'show the owner-controlled setup path' is ambiguous about whether it returns instructions or a URL. It weakly distinguishes itself from send/read siblings but leaves the core purpose imprecise.

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?

There is no explicit when-to-use guidance and no alternative is named among the six siblings (list_inbox, send_once, etc.). The setup/verification context is only implied. An agent must infer that this is a pre-flight check rather than a listed action.

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