aliasmail-mcp

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

No annotations exist, so the description carries the full burden. It does disclose that the operation produces authentication verdicts, a hop transit timeline, and a security grading — useful output-shape context for a pure read-only analysis. However, it never states it is read-only/non-mutating, says nothing about input validation failures (malformed headers), rate limits, or what the grade scale means.

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-loaded with the tool's identity and followed by the analyzed artifacts. No filler, though the colon-list construction is terse to the point of omitting any operational guidance.

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 one-parameter analyzer with no output schema and no annotations, the description gives the analytical coverage but not the result shape (field names, grading scale, how hops are reported) or failure behavior. Adequate to know what the tool is for, but thin for knowing what will come back.

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 100% for the single required parameter 'headers', already documented as 'Raw RFC 822 email headers string'. The description adds no format detail (e.g., whether Received: ordering matters, whether the body must be excluded), so 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 (analyze) and resource (RFC 822 email headers) plus the concrete artifacts it inspects: SPF, DKIM, DMARC verdicts, relay hops, and a security grade. It is distinguishable from siblings like check_spam_score or check_dns by scope, though it never names those siblings to draw the contrast 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?

Usage is only implied: the phrase 'raw RFC 822 email headers' signals the input must be full raw headers rather than a parsed summary, but there is no statement of when to prefer this over aliasmail_check_spam_score or aliasmail_check_dns, and no prerequisites or exclusions are given.

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. 'Check' implies a non-mutating lookup, and the description adds real semantic context by defining both sides of the verdict (disposable provider vs. legitimate corporate infrastructure), but it says nothing about the response shape, confidence signals, or whether results are cached/rate-limited.

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 verb and the decision it produces, with zero filler. Everything present 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?

The input side is complete, but with no output schema and no annotations, the description is the only place an agent could learn what the check returns (boolean, verdict enum, score?) and it omits that entirely. For a lookup tool an agent must branch on, this is a meaningful 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?

The single 'target' parameter is fully documented in the schema, including worked examples for both accepted forms (bare domain and full address). The description adds no meaning beyond that, so the baseline 3 applies for a fully covered 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?

States a specific verb and resource ('Check whether an email address or domain...') plus the exact classification being made: disposable/burner versus legitimate corporate infrastructure. It is clear on its own, but it never distinguishes itself from the nearby sibling aliasmail_validate_email, which an agent could easily mistake for this check.

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 by the purpose statement — an agent can infer 'use before sending to avoid burner addresses' but nothing is stated about when to reach for this versus aliasmail_validate_email or aliasmail_check_dns. No exclusions, preconditions, or alternatives are named.

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. 'Real-time' usefully signals live external DNS lookups, and the enumerated checks clarify scope, but the description does not state whether the operation is read-only, what happens on lookup failure, or what kind of result is returned.

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 a single front-loaded sentence with no wasted words. It immediately states the operation, the real-time nature, and the exact records audited.

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 one-parameter tool with full schema coverage, the description adequately states the checks performed. However, with no annotations and no output schema, it does not explain result structure, failure behavior, or selection guidance against sibling diagnostic 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 schema has 100% description coverage and fully documents the single 'domain' parameter with examples. The description does not add any parameter-level detail beyond what the schema already provides, so the baseline of 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?

The description uses a specific verb-plus-resource ('DNS audit of domain') and enumerates the exact record types checked: MX, SPF, DMARC, and DKIM. It is clearly a DNS-record checker rather than an email-content or deliverability tool, but it does not explicitly differentiate itself from sibling tools such as aliasmail_validate_email or aliasmail_analyze_headers.

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 says what the tool does but gives no guidance on when to use it versus alternatives such as aliasmail_validate_email, aliasmail_check_disposable, or aliasmail_health_check. There are no stated preconditions, exclusions, or routing cues for choosing this tool.

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 behavioral burden. It helpfully discloses that the tool checks spam heuristic triggers, capitalization ratios, link density, and deliverability risk, but it does not mention whether the operation is read-only, what the result shape is, or any permission or rate-limit considerations.

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 a single front-loaded sentence with no filler. It efficiently states the evaluation target and the dimensions checked.

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 analysis tool with full schema coverage, the description gives enough to understand what is checked. However, because there is no output schema, the description does not explain the return value or score format, which leaves a meaningful gap for invocation planning.

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 both parameters, subject and body, are already documented in the schema. The description adds no parameter-specific meaning beyond referring generically to 'email copy', which is adequate but not enriching.

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: evaluate email copy for spam score and deliverability risk. It clearly distinguishes the tool's analytical purpose from sibling tools like email validation or header analysis, though it does not explicitly name a sibling alternative.

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 'Evaluate email copy' implies checking content before sending, but there is no explicit when-to-use or when-not-to-use guidance. No alternatives or prerequisites are mentioned, leaving usage context 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 and no output schema, the description carries the full behavioral burden. 'Defuse' implies neutralization or removal, but it does not state whether the input is mutated, whether sanitized HTML is returned, what exactly is removed, or what side effects exist.

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?

It is a single front-loaded sentence with no filler. The action and the targeted tracking mechanisms are stated immediately.

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 low-complexity one-parameter tool, the description is minimally adequate to invoke it. However, with no annotations or output schema, it leaves the return value and sanitization behavior unspecified, so the agent cannot confidently predict the result.

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?

There is only one parameter, 'html,' and schema description coverage is 100%, so the schema already documents it as raw HTML to sanitize. The description adds no format or syntax detail beyond the schema, so the baseline score of 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?

The description uses a specific verb pair, 'scan and defuse,' with concrete targets: 1x1 tracking pixels, read receipt beacons, and redirect links in email HTML. It is clearly distinct from sibling tools that fetch, validate, or analyze email.

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 no explicit when-to-use guidance, prerequisites, or named alternatives. The 'in email HTML' scope implies context, but it does not tell an agent when to choose this over get_message or analyze_headers.

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 does carry real weight and does disclose several traits: zero-log operation, no registration, and immediate readiness. It omits key behaviors such as inbox lifetime/expiry, whether the handle must be unique or what happens on conflict, and what address is returned, which matter for a mutation/creation 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?

Three short, front-loaded sentences with zero filler; the core action leads and the supporting conditions follow.

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 creation tool with full schema coverage and no output schema, the description is nearly sufficient. The main omission is inbox lifetime and what identifier the caller receives, which the agent would need to chain into the wait/get 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?

Schema description coverage is 100% and the single optional 'handle' parameter is fully documented with examples in the schema. The description adds no additional semantics about the handle (e.g. uniqueness rules), so the baseline of 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 ('Generate an instant ... disposable temporary email inbox') plus the service context and URL. It is unmistakably a creation tool, clearly distinguished from the sibling read/wait/check tools that operate on existing inboxes.

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 names use cases ('receive verification emails, OTP codes, or test messages') and the no-registration condition, which implies when to reach for it. However, it never explicitly routes the agent to a sibling (e.g. use wait_for_code after creation) nor states when this tool is not appropriate.

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?

While there are no annotations, the description provides highly valuable behavioral context by enumerating the output contents: 'body text, sanitized HTML, headers, and extracted links/codes.' This tells the agent exactly what data structure to expect upon a successful 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?

The description is a single, impactful sentence. Every word contributes to specifying the tool's function and scope, making it perfectly concise and well-structured.

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 that there is no output schema, the description is highly complete by listing all major components of the expected return value (HTML, headers, links). This is critical for an agent to understand the result and plan subsequent actions.

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?

Since the schema coverage is 100%, the baseline score is 3. The description does not provide any semantic value beyond the basic function and parameters listed in the 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 clearly identifies the action ('Retrieve full content') and the resource ('specific email') and specifies the scope as an 'AliasMail temporary inbox.' It implicitly distinguishes itself from sibling tools like aliasmail_get_messages.

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 heavily implied; one uses it when needing the full content of a known message ID. However, it does not explicitly state a 'when' or 'when not' scenario (e.g., compared to retrieving a list of messages), resulting in a score of 3.

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?

Since no annotations are present, the description carries the full burden of behavioral disclosure. It explicitly states what the resulting list of messages contains (subject, sender, timestamp, and snippet), which is critical operational context for a retrieval 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 definition is extremely concise and front-loaded. It delivers the purpose and the core context (the service URL) in a single, efficient statement.

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?

The description is highly complete for a listing tool. By including the base URL and detailing the contents of the returned messages, it provides maximum utility even without an output schema to define data structure.

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 input schema coverage is 100%, meaning the description doesn't need to repeat or elaborate on parameter functions. While it provides the base URL for context, it adds no semantic meaning beyond what is already structured.

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 tool clearly fetches emails from a specific resource (AliasMail temporary inbox). It is distinct from single-message retrieval tools (aliasmail_get_message) and waiting tools, making its purpose 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?

While it doesn't explicitly contrast itself against alternatives, the nature of a 'get_messages' tool implies it should be used when a user needs to browse or check for multiple emails rather than waiting for or retrieving one specific message.

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 provided, so the description carries the disclosure burden. 'Check' implies a non-mutating probe, but the description doesn't state whether it requires auth, whether it can be rate-limited, or what status fields are returned (and there is no output schema to cover that).

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 front-loaded sentence with no filler. 'Health and operational status' is mildly redundant but does not bloat the definition.

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 annotations and no output schema, the agent has no structured signal about what a health check returns (status enum, component breakdown, latency) or how to interpret a failure. The description names the check but leaves the result contract entirely unspecified.

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 there is nothing for the description to clarify; the baseline for a parameterless tool 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?

The description gives a specific verb ('Check') and a specific scope ('health and operational status of the AliasMail infrastructure and API services'), which is clearly distinct from the message/inbox/validation siblings. It stops short of naming an alternative, but the resource 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?

Use is only implied – an agent can infer this is a diagnostic/availability probe used before or when other calls fail, but the description states no explicit when-to-use or when-not-to-use condition relative to siblings like aliasmail_check_dns.

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 disclosure burden. It usefully names the four verification layers performed, which is real behavioral content beyond the name. However, it says nothing about what happens on a failed validation (exception vs. a negative result), whether this performs live network/DNS lookups with associated latency or rate limits, or what the response contains — all material for a tool that returns no 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?

One front-loaded sentence with the core purpose first and the enumerated checks second — no filler, no repetition. The inline URL is arguably extra, and a short second sentence on usage would earn its place more than the link does.

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 one-parameter tool this is close to sufficient, but there is no output schema and the description never indicates the shape of the result — the agent cannot know whether it receives a boolean, a per-check breakdown, a score, or a normalized address. Given it advertises four distinct checks, that return-shape gap matters.

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?

There is a single required parameter at 100% schema description coverage ('The email address to validate'), so the schema already does the work and the baseline would be 3. The description adds modest value by implying the input is the address under test and that normalization/typo reasoning happens server-side, but it offers no guidance on accepted formats or edge cases.

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 ('Deep email address validation') and enumerates the checks performed: RFC 5322 syntax, MX resolution, typo detection, disposable flagging. That makes the scope concrete, but it never distinguishes itself from siblings that overlap heavily (aliasmail_check_disposable, aliasmail_check_dns), so an agent can't tell from this text alone which tool to pick for a single-purpose check.

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 a pre-send or signup-form validation step. There is no explicit 'use this when...' statement and no mention of the obvious alternatives (aliasmail_check_disposable, aliasmail_check_dns), even though this tool subsumes part of their function.

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 provided, so the description carries the full behavioral-disclosure burden. It explains autonomous polling and parsing, but omits important behavior such as what happens on timeout, what the tool returns, error conditions, and whether the inbox must already exist.

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 tightly written sentences with the core purpose front-loaded. The second sentence adds useful value by emphasizing automation and removal of manual polling/regex parsing.

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 long-polling and parsing tool with no annotations and no output schema, the description is missing key operational context. It does not describe the return payload, timeout behavior, empty-result behavior, or prerequisites, leaving the agent under-informed for reliable 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 100%, so parameter meanings are already well documented in the input schema. The description adds that it looks for a 4-8 digit OTP or confirmation link, but does not add parameter-specific guidance beyond the 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?

States a specific verb and resource: it polls an AliasMail inbox until a verification/signup email arrives and parses an OTP code or confirmation link. The operation is clear, though it does not explicitly distinguish itself from the sibling aliasmail_wait_for_email.

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 for signup/verification flows, and the description says it eliminates manual polling and regex parsing. However, it gives no explicit when-not guidance, prerequisites, or comparison to the closely named sibling aliasmail_wait_for_email.

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 behavioral burden. It does not state what happens on timeout, whether matching messages are consumed or marked read, whether old existing emails can match, or what the polling/waiting cost is.

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 front-loaded sentence with no wasted words. It is appropriately compact, though slightly too terse for a blocking tool with five parameters.

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, no annotations, and five parameters including timeout behavior. The description omits the return value, timeout semantics, and whether the wait is destructive/consuming, which are needed to call this 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 coverage is 100%, so the schema documents address, filters, timeout, and poll interval. The description only echoes the optional sender/subject filtering and adds no meaning beyond the 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?

States a specific verb and resource: waits for new incoming email on an AliasMail temporary inbox, with optional sender/subject filtering. It is distinguishable from immediate-fetch siblings, but it never names or contrasts with aliasmail_get_messages or aliasmail_wait_for_code.

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 verb 'wait' implies blocking until a new email arrives, which implicitly contrasts with the immediate fetch siblings. However, there is no explicit when-to-use guidance, no exclusions, and no statement about when to prefer aliasmail_wait_for_code.

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