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

With no annotations the description carries the full burden, and it delivers meaningful traits: the address is unique, immediately receivable, needs "nothing to set up," and notably "Makes no API call." That last point usefully tells the agent there is no network round-trip, rate limit, or auth wall. It omits any note on persistence, expiry, or cleanup expectations.

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, front-loaded with the core purpose and escalating to a usage rule and a behavioral caveat. No sentence is filler; even the terse "Makes no API call" 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-required-parameter generator with no output schema, the description covers purpose, the intended per-test usage pattern, and the key behavioral fact that no API call occurs. It could go further on what the returned address looks like or whether addresses expire, but nothing critical to correct invocation 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 100%, so the schema already explains domain (with default and privacy advice) and prefix. The description adds nothing about either parameter, which is acceptable when the schema does the work. Baseline 3 applies.

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 ("Return a new, unique address that can receive email immediately") and implicitly separates itself from the consumer siblings (wait_for_email, read_email, delete_emails). It never names a sibling or explicitly contrasts its role, so it stops short of a 5.

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?

Gives concrete usage direction: "Use one address per test so tests never read each other's mail," which tells the agent the intended lifecycle pattern. There is no when-not guidance or explicit routing to alternatives, but the context for calling it is clear.

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?

destructiveHint=true already tells the agent this is a destructive operation, and the description's omitting-messageId clause usefully adds that the bulk case wipes an entire address rather than one message. However it never states irreversibility, whether deletion can be undone, or any auth/ownership requirement — gaps that matter for a destructive tool with a low annotation bar.

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 branching behavior front-loaded and the motivating use case last. 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 simple two-parameter tool with no output schema, the description covers both the single and bulk modes and the intended cleanup scenario. The remaining gap is that a destructive operation is not flagged as irreversible and messageId's provenance is unstated, but the destructiveHint annotation partially compensates.

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 carries the burden, and it does convey the key semantics: messageId present means one message, absent means all mail at address. It does not explain the format/origin of messageId (e.g. obtained from list_emails or read_email) nor the address format, so coverage is good but not complete.

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 (delete) and resource (email/emails), and explicitly disambiguates its two operating modes: single message via messageId, or the whole mailbox at an address when messageId is omitted. Among siblings (list_emails, read_email, create_test_address) only this tool deletes, so its role 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?

"Clean up after a test" gives one intended context and hints at a paired workflow with wait_for_email/read_email, but there is no guidance on when not to use it, no warning about permanent loss, and no mention of constraints (e.g. only owned test addresses). The usage context is implied rather than spelled out.

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, but it does add a genuine behavioral fact: mail to a private domain is visible only to the account. It still omits read-only confirmation, pagination behavior, and what the account scope actually means for results.

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, no filler, with the primary action front-loaded and the usage hint following immediately. 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?

For a zero-parameter list tool with no output schema, the description covers what is listed, the visibility semantics, and the follow-up call. It could state the return shape (e.g. a list of domain names) explicitly, but 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?

The tool takes zero parameters, so the baseline is 4. The description goes slightly beyond by naming the downstream parameter slot (`domain` on create_test_address) where a returned value is consumed, which helps an agent chain calls.

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 tied to the Mailsac account ('List the private domains on this Mailsac account'), which is unambiguous about what is returned. It does not differentiate against sibling list tools (list_emails, list_domains vs them) beyond naming create_test_address as a downstream consumer.

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 implies the use case by explaining that a listed domain can be passed as `domain` to create_test_address, which is a helpful workflow pointer. However, it never states when to call this tool versus alternatives such as list_emails, nor any prerequisites or exclusions.

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. It usefully discloses ordering ('newest first'), the exclusion of bodies, and scope ('currently stored'), but says nothing about pagination, result limits, permissions, or what 'One operation' actually means — which reads as cryptic rather than informative.

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?

One sentence, front-loaded with the core action and result shape, with the ordering and body-exclusion constraints trailing compactly. 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?

With no output schema and no annotations, the description does the important work of describing the return set (emails, newest first, bodies omitted). The main gaps are pagination/limits and the meaning of the trailing 'One operation', which are not explained.

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% for the single 'address' parameter; the schema only declares type=string/format=email. The description adds that the address selects the mailbox whose emails are listed, which is minimal but consistent with the schema's format hint.

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+resource ('List the emails') scoped to 'an address', and it distinguishes itself from read_email by noting there are 'no bodies'. It does not name siblings explicitly, but the resource and result shape are 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 implied rather than stated: the '(no bodies)' note hints that read_email is the tool for message content, and 'newest first' signals a listing/scan use case. There is no explicit when-to-use or when-not-to-use guidance against wait_for_email, delete_emails, or list_domains.

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 burden, and it does disclose what each format returns (links/actionLink/codes for text, HTML body, MIME source, parsed headers). It omits whether reading marks the message as read, permission requirements, and error behavior, so it is partially complete but not rich.

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?

One tight sentence, front-loaded with the core purpose before enumerating format behaviors. The semicolon-dense format list is compressed but every clause adds 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?

With no output schema and no annotations, the description covers the main gap by explaining the return shape for each format. A simple read tool needs little more, though side effects and failure modes are unaddressed.

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, and it fully explains the format enum's four values and their outputs. address and messageId remain undocumented, though their names and required status make their meaning self-evident.

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 ('Read one email'), with 'one' implying single-message scope versus the sibling list_emails. It does not name an alternative tool or clarify the boundary with wait_for_email, so the differentiation is only implied.

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 explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The reader can infer that a messageId and address are prerequisites from the required parameters, but the description itself offers no routing 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?

With no annotations, the description carries the full burden. It usefully discloses the polling cost ('Each poll uses one Mailsac operation') and the return payload, but never states what happens when the timeout elapses (error, empty result, partial match) or whether the call blocks. That failure-mode gap is material for a wait-style 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?

A single dense sentence front-loads the core action and then lists the returned artifacts without padding. Slightly overloaded by packing the full return list and the polling-cost note together, but every clause carries information.

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, and the description does cover the returned fields, which is the main need. However, for a 6-parameter, timeout-driven tool with zero annotations, it omits timeout/failure semantics and concurrency behavior, leaving a real gap.

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 83%, so the schema already documents address, fromContains, receivedAfter, subjectContains and timeoutSeconds. The description adds no filter syntax or matching semantics beyond 'matching email', so it does not extend the schema meaningfully.

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 ('Poll an address until a matching email arrives') and enumerates what is returned, making it clearly distinguishable from siblings like list_emails and read_email. The purpose is unambiguous 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?

Usage is implied by the polling behavior — an agent infers this is for awaiting an inbound message rather than reading one already present — but no sibling is named and there is no explicit when-not guidance. Adequate but leaves the choice against read_email/list_emails to inference.

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