MailVakt

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

Annotations declare idempotency and non-destructiveness, and the description goes well beyond them: it discloses the domains:write permission requirement, that ownership is not verified, that DNS is not modified, and that reporting does not begin until the user publishes the rua address. These are exactly the side-effect boundaries an agent needs before invoking a mutating 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?

Four sentences, each front-loaded and carrying distinct information: purpose, return value, idempotency, and permission/side-effect boundaries. No filler or repetition.

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 compensates by describing the return (the rua reporting address and account entry). Combined with the permission, idempotency, and non-side-effect disclosures, an agent has everything 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?

Only one parameter, and schema description coverage is 100% ('The domain to add, e.g. example.com'), so the schema already carries the semantics. The description's 'Takes a domain' adds nothing beyond 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 resource (add a domain), scopes it to the signed-in user's MailVakt account, and names the domain's purpose (DMARC report collection). This distinguishes it clearly from siblings like list_domains or diagnose_domain.

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?

Implies the usage context (enrolling a domain for DMARC collection) and explicitly addresses the repeat-call case ('Repeated calls for the same account and domain return the existing entry'). It does not name an alternative tool or state when not to use it, so it falls short of a 5.

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 and that the tool performs no external writes, but the description adds important behavioral boundaries: it parses text without external DNS or HTTP lookups, does not independently verify DKIM signatures, and cannot establish the receiving provider's exact spam-filter decision. These caveats go well beyond the annotation and prevent an agent from over-trusting the 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?

Three sentences front-load the core purpose, then add output details and critical caveats without any wasted words. Every sentence contributes either function, output scope, or behavioral limits, and the exclusion of body text is placed last as a final input constraint.

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 required string parameter with no output schema, the description is complete: it explains what the tool does, what it returns, what it does not do (no external lookups, no DKIM verification), and what not to supply. No output schema exists, so the enumerated return fields fully cover the result scope.

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 single parameter's type and constraints are fully documented in the schema. The description reinforces the parameter's meaning by clarifying that headers must be provided as raw text and not the body, adding modest value. Baseline 3 is appropriate when the schema already handles the parameter definition.

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 (raw email headers) with a clear goal: investigate authentication or delivery issues. It also enumerates the concrete outputs (SPF, DKIM, DMARC results, alignment, sending IP, detected issues), making its function unmistakable and distinct from siblings like diagnose_domain.

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 specifies the input context (raw headers copied from 'Show original') and explicitly excludes situation-dependent alternatives ('Provide headers only, not the message body'). It gives clear when-to-use context (auth/delivery issues) but does not name a specific sibling to use instead, so it falls just short of a 5.

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?

Beyond the readOnly/destructive annotations it discloses real limits: uses DNS and policy-file lookups, never changes DNS, and does not guarantee inbox placement. It also notes fresh=true bypasses cached results, which an agent cannot infer from annotations alone.

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 are front-loaded with the purpose before usage, parameters, and return/limits. Dense but each clause earns its place; 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, the description usefully enumerates what is returned (graded scorecard, findings, proposed DNS fixes, report permalink) and states the tool's operational bounds. An agent has enough to invoke it correctly and set expectations.

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 all four parameters (domain, checks, dkim_selectors, fresh) are already documented. The description only restates 'optional checks and DKIM selectors, and fresh=true,' adding no syntax or default detail beyond the schema, 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 precise verb (audit/diagnose) and resource (a domain's SPF/DKIM/DMARC/MX/BIMI/MTA-STS/TLS-RPT configuration), enumerating the exact check surface. It is clearly distinguishable from siblings like generate_dns_records or analyze_email_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?

Explicitly frames the trigger condition: 'when troubleshooting email authentication or spam delivery.' It gives a clear context for use but does not name which sibling to prefer when, e.g., analyzing headers vs. diagnosing a domain.

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, openWorldHint=true and destructiveHint=false. The description adds real context beyond them: it explicitly states it does not publish records or change DNS, that lookups are public and possibly cached, and that provider-specific values may require user input. This goes meaningfully past the structured safety hints.

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?

Dense but well front-loaded: capability statement first, then goal semantics, return types, caveats, and side-effect disclaimer. Four sentences with essentially no filler, though the run of caveats makes it slightly heavier than necessary.

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 still enumerates what is returned (typed SPF/DKIM/DMARC/MTA-STS/TLS-RPT proposals or provider setup instructions). Combined with the explicit no-publish disclaimer and caching note, 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 still adds value the schema lacks: it states that 'baseline is the default' for the goal parameter, explains both goal modes are supported, and clarifies that providers are optional and inferred when 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?

States a specific verb (propose/generate) and resource (email-authentication DNS records and policy files: SPF, DKIM, DMARC, MTA-STS, TLS-RPT) plus the inputs it consumes (DNS configuration, optional providers). This clearly distinguishes it from siblings like diagnose_domain or add_domain, which do not generate record proposals.

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 useful in-tool guidance on the goal choice ('baseline (monitoring) or enforce goals; baseline is the default') and notes when user input may be required for provider values. However, it never says when to use this tool versus alternatives such as diagnose_domain or add_domain, leaving sibling routing 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?

Annotations already declare this a safe read (readOnlyHint/destructiveHint=false), yet the description adds material context beyond them: required scopes (domains:read, reports:read), empty-result behavior (zero totals when no reports), and the error case (domain not in account). It also clarifies it mutates nothing, closing any ambiguity about report generation.

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 dense sentences, front-loaded with the purpose, then window/return shape, then permissions and edge cases. No filler clauses; each sentence carries distinct 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, the description still enumerates what is returned (report and message totals, DMARC pass/fail counts, per-source SPF/DKIM alignment and receiver actions) plus empty and error behavior. Nothing needed to invoke or interpret the call 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 documents both parameters, including the 'one of the user's domains' constraint and the day bounds. The description largely restates the 1-to-90-day/default-7 window and repeats the account-scoped domain constraint without adding new format or syntax guidance, so the 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 (Summarize) and resource (received DMARC aggregate reports) with scope qualifier (for a domain already in the user's account). This clearly separates it from siblings like add_domain, generate_dns_records, or analyze_email_headers, which operate on different objects.

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 the precondition (domain must already exist in the account) and a when-not clause ('Does not add domains or generate report traffic'), which implicitly routes users to add_domain/generate_dns_records for those tasks. It stops short of naming an explicit alternative for domain-level diagnostics such as diagnose_domain.

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?

Goes well beyond the readOnly/destructive/openWorld annotations by disclosing the returned status set (pending, received, expired), the finding categories returned on success, that processing failures surface as errors, and an important access-control caveat that anyone holding the test ID can retrieve it. This is behavioral context the annotations cannot convey.

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 tight sentences, each earning its place: purpose, return values, error behavior, access caveat, and scope limitation. The core action and its dependency on start_inbox_test are front-loaded.

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 compensates by enumerating status values and finding categories, and it flags the failure mode and the credential-scoping rule. Nothing an agent needs to call or interpret this tool 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 coverage is 100% and the single parameter is already documented as 'The id returned by start_inbox_test', so the schema carries the semantic load. The description reinforces the same origin but adds no new format, pattern, or validation detail beyond it, making the baseline 3 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 resource ('Read a MailVakt email-receipt test') and ties the input to the sibling that creates it ('the ID returned by start_inbox_test'). This distinguishes it cleanly from start_inbox_test and the other domain-oriented 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?

Gives real usage constraints: 'use only an ID supplied by the user or created in this conversation' and an explicit scope exclusion ('Does not measure placement at other mailbox providers'). It does not spell out a full when-to-use vs. alternative decision, but the prerequisite relationship to start_inbox_test 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?

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds value beyond them by disclosing the required 'domains:read' permission, that it takes no input, and that an empty list is returned when the account has no domains.

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: purpose and payload first, then constraints/permissions, then usage and scope exclusion. Every sentence earns its place with 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, the description still conveys what comes back (domains plus their DMARC reporting address) and the empty-list edge case, which is enough for a no-argument list tool. A little more on ordering or pagination would be needed for 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?

Zero parameters, so the baseline is 4; the schema is empty and there is nothing to misinterpret. The description's 'Takes no input' is consistent with the schema but adds no new semantic detail.

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 (List) and resource (domains) scoped to the signed-in user's MailVakt account, and specifies what is included (each domain's DMARC reporting address). The added clause 'does not enumerate domains belonging to other users' sharpens scope so the agent can separate it from sibling tools like add_domain or diagnose_domain.

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 states when to use it ('to find the account's available domains before requesting DMARC summaries'), which routes the agent toward get_dmarc_summary as the follow-up, and states the exclusion (does not enumerate other users' domains). Both the when and when-not are present.

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 declare a non-read-only, non-destructive, closed-world write, and the description adds real context beyond that: a new test is created on every call (non-idempotent), an expiry window applies, and the user must act externally before it lapses. It stops short of saying what happens if the message arrives after expiry or whether tests can be re-read after expiration, so a 4 rather than 5.

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-loaded with the core action, then the return values, then the workflow and exclusions; every sentence carries distinct information. Slightly long at five sentences, but no sentence is pure filler, so it sits just below ideal brevity.

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 carries the return contract ('a test ID, unique recipient address and expiry time') and explains the external action needed to make the test meaningful. For a one-parameter, closed-world tool, nothing an agent needs to invoke it correctly 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 coverage is 100% for the single parameter, so the schema already documents expected_from_domain with an example. The description only restates it as 'an optional expected sender domain', adding no format, matching, or validation detail beyond the schema baseline.

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 ('Create an email-receipt test in MailVakt') and goes further to say what it explicitly is not ('Does not send email or measure inbox-versus-spam placement at Gmail, Outlook'), which separates it from the diagnostics siblings like diagnose_domain and analyze_email_headers. The follow-up read path via get_inbox_test is named, so an agent can distinguish it from its sibling without opening a 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?

Gives the full when-to-use workflow: call this to create the test, send a message to the returned address before expiry, then call get_inbox_test for the result. It also supplies the when-not ('does not send email or measure inbox-versus-spam placement'), leaving nothing to inference.

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