postbox-tools

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavioral context the annotations cannot convey — that the analysis is offline and therefore scoped away from SMTP-dependent checks, and that its score is not authoritative. It does not describe the shape or richness of the returned findings, which is the remaining gap.

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. The core action comes first and the limitation plus alternative follow, with the capitalised 'IMPORTANT LIMITS' flagging the constraint an agent most needs before choosing this 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?

For a single-parameter read-only analysis tool with no output schema, the description covers purpose, input expectations, offline limitations, and the better alternative. The only omission is any indication of what the analysis returns or how trustworthy partial results are, which matters somewhat given the explicitly non-authoritative score.

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 exists and schema coverage is 100%, so the schema already explains that the value must be the complete raw source with headers and body. The description's '(.eml source: full headers + body)' restates rather than extends that, 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 and resource: 'Run a deliverability/content analysis on a raw RFC 822 email (.eml source: full headers + body).' It also names the sibling tool that gives the authoritative result, so the agent can distinguish this file-based analyzer from create_mailtest without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly defines the boundary condition: 'with no live SMTP session, SPF, blacklist and reverse-DNS cannot be verified from a file' and redirects to create_mailtest 'for the authoritative score.' Both the when-not and the alternative are stated outright rather than 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 the operation is read-only, non-destructive, and open-world. Beyond that, the description adds useful behavioral detail: it distinguishes answer-engine versus training crawler access in robots.txt, treats llms.txt and ai.txt as informational signals, and states that the output includes an A-F grade, per-crawler access, and findings. It does not mention rate limits or caching, but its behavioral disclosure is substantially richer than the 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?

The description is compact and front-loaded: the purpose and resource come first, followed by the specific files checked and the output shape. Every clause adds useful information, and there is 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?

For a single-parameter read-only grading tool with no output schema, the description supplies enough context to call it correctly and to understand what will be returned. It identifies the public files analyzed, the grading approach, and the output components (grade, per-crawler access, findings), leaving no material gaps for an agent.

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, 'domain,' and the input schema already documents it with an example. The description adds the context that the domain determines which public files are fetched and graded, but it does not add format, normalization, or validation semantics beyond the schema. With 100% schema coverage, a baseline of 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?

The description uses a specific verb, 'Grade,' with a clearly defined resource: how discoverable a website is to AI answer engines. It enumerates the exact public files examined (robots.txt, sitemap.xml, llms.txt, ai.txt) and names the answer engines considered, making the tool's scope distinguishable from email and domain 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?

The description gives a clear context for use: assessing AI answer-engine discoverability from public files. It does not explicitly state when not to use the tool or name an alternative, but the sibling tools focus on email authentication, blacklists, domain age, redirects, and WHOIS, so the use case is unambiguous by contrast.

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/openWorld annotations, it discloses the actual behavior: a DNS TXT lookup followed by fetching the referenced logo and validating it against a specific SVG profile. It also states the two verification limits (no certificate validation, no DMARC check), which prevents over-reading the result. It does not describe error/timeout behavior for unreachable logos, keeping it from a 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?

Two sentences, the primary action front-loaded and the scope limits placed after. Every clause carries information; nothing is redundant with the title.

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 read-only lookup with no output schema, the description covers what is inspected, what is validated, what is merely reported, and what is deliberately excluded. That is sufficient for an agent to call it correctly and interpret 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?

With a single parameter at 100% schema description coverage, the schema already documents 'domain' with an example. The description confirms the parameter is interpreted as an apex domain whose BIMI setup is probed, but adds no format or edge-case detail (subdomains, IDN) 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?

The description names a specific verb and resource ('Check a domain's BIMI setup') and enumerates exactly what is examined: the default._bimi TXT record, the l= logo, SVG Tiny P/S validation, and the a= certificate reference. It also explicitly distinguishes itself from check_spoofability, so an agent can separate it from 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?

It gives a clear usage boundary by stating it does not verify the certificate or the DMARC policy and routing DMARC enforcement checks to check_spoofability. It stops short of a full when-to-use framing (e.g., when to run this vs. other domain checks), but the exclusion plus named alternative covers the main ambiguity.

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 cover the safety profile (readOnlyHint=true, openWorldHint=true, destructiveHint=false), so the description earns credit for adding real context: which blacklists are consulted, that no DNS resolution happens, and that results are reported per list. It omits operational behavior an agent might care about, such as rate limits on DNSBL queries or how unlisted/timeout states are reported, which keeps it short of a 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?

Three sentences, front-loaded with the domain case before the IP case, and each sentence carries distinct information. The only soft spot is 'and others', which is vague but does not cost the agent anything actionable.

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 read-only lookup with no output schema, the description covers input routing, list coverage, and the shape of the return ('per-list listing status'). What is left implicit is the per-list result fields and how an inconclusive or timeout response appears, which is a minor gap rather than a blocking one.

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 schema already explains that a domain goes to domain blacklists and an IPv4 to IP blacklists, so the baseline is 3. The description adds meaning the schema does not: the named list providers, the count of IP lists (24), and the explicit statement that domains are not resolved to IPs.

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 (check) and resource (domain/IP against blacklists), and enumerates the actual list providers (Spamhaus DBL, SURBL, URIBL, ZEN, Barracuda, SpamCop). None of the sibling tools (whois_lookup, check_bimi, check_spoofability, etc.) do blacklist lookups, so the agent can route here unambiguously.

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 input type drives usage: pass a domain to hit domain blacklists, an IPv4 address to hit the 24 IP blacklists. The clause 'Checks the exact target given: domains are not resolved to IPs' is a genuine usage caveat that stops an agent from expecting IP-list coverage for a domain. No explicit exclusions or named alternatives, but no sibling overlaps enough to need them.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds useful context that the data comes from public DNS and a live lookalike-domain lookup (explaining the open-world behavior) and that output is an A-F grade with findings. It does not mention latency, rate limits, or behavior on malformed/unresolvable 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?

A single front-loaded sentence with no filler; the what, the sources, and the return shape all appear in one pass. Nothing repeated from the title is wasted beyond a brief restatement.

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 read-only single-parameter tool with no output schema, the description supplies the missing return semantics (A-F grade plus findings) and names the evidence domains inspected. Slightly incomplete on failure modes and timing for the live lookalike lookup, but nothing essential to invocation is absent.

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 schema already defines 'domain' with an example. The description confirms the domain is what gets graded but adds no format constraints, normalization rules, or edge cases beyond the schema, 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 ('grade how exposed a domain is to email spoofing and business email compromise') plus the evidence sources (SPF, DMARC policy strength, alignment, live lookalike domains). This clearly separates it from siblings like check_bimi or check_blacklist, which cover adjacent but different checks.

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 intent is implied — run it on a domain to assess spoofing/BEC exposure — but there is no explicit when-to-use versus when-not guidance, and no routing to alternatives such as check_bimi for BIMI-specific posture or check_blacklist for reputation. An agent can infer the use case but must reason about sibling selection unaided.

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 readOnlyHint=false, destructiveHint=false, openWorldHint=false, but the description adds genuinely new behavioral facts: a disposable address is returned, the flow pauses on an out-of-band human action (sending an email), and scoring only materializes on a later call. It does not say whether addresses expire or can be reused, which is the main remaining gap.

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, front-loaded with the action and the artifact, with the prerequisite user action called out in caps before the follow-up tool. The parenthetical checklist is dense but earns its place by explaining what the score covers.

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 parameters and no output schema, the description covers what an agent needs: what is created, that the response contains an address, the required human step, and how the result is later retrieved. Only lifetime/expiry of the disposable address and reuse rules are left 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 schema to document and the baseline of 4 applies. The description correctly notes that the address is "returned" rather than supplied, which is the only parameter-adjacent fact that matters here.

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 a disposable test address") and immediately scopes what it is for: a full email deliverability audit with an enumerated check list. It is clearly distinguishable from siblings like get_mailtest_result, which is named as the follow-up step.

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 gives an explicit usage sequence: create the address, have the USER send an email from the system under test to that address, then call get_mailtest_result. That is unusually clear routing guidance, though it does not state when this tool should be avoided (e.g., when an address already exists).

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 and non-destructive semantics, so the description's job is narrower. It adds interpretive value by explaining what the result means for deliverability. It omits edge behavior for unregistered, private, or unsupported-TLD domains, which keeps it from a 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?

A single sentence with the concrete return values front-loaded and the parenthetical earning its place by telling the agent why the result matters. 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?

For a one-parameter read tool with full schema coverage, the description is nearly sufficient and partly compensates for the missing output schema by naming the returned values. The remaining gap is behavior on missing or private WHOIS data and how this differs from the check_* siblings.

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 exists and the schema documents it fully with an example format, so the baseline is 3. The description adds no format, normalization, or subdomain-handling detail beyond the schema's example.

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 (get) and resource (domain age) and names the concrete outputs: registration date and age. It stops short of differentiating from the sibling whois_lookup, which plausibly also surfaces registration data, so an agent cannot route between the two on description alone.

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 parenthetical 'young domains have weak sending reputation' implies the tool is for sender-reputation assessment, which gives the agent a usage context. There is no explicit when-to-use/when-not guidance and no mention of whois_lookup as the alternative for broader registration data.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the timing precondition, but it does not say what happens when the result is not yet available (error vs. pending score) or whether results are cached or expire, which is the main behavioral nuance for a polling-style read.

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 sentence with no wasted clauses, and the precondition is placed at the end where it reads naturally. It is slightly compressed by the combined "score and breakdown" phrasing, but nothing is extraneous.

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, read-only tool with full annotation coverage and no output schema, the description covers the input source, the return contents, and the timing precondition. The only gap is the not-yet-available state, which is minor for this complexity level.

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 parameter has 100% schema description coverage stating it is the test id returned by create_mailtest, and the description only restates that same fact. Baseline 3 applies since the schema already carries the semantics.

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 specific verb ("Fetch") and specific resource ("the score and breakdown of a mail test"), and ties it to the create_mailtest sibling, so an agent can tell it apart from create_mailtest or the check_* tools without opening any 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?

It states the precondition for calling: the test must have been created and the user must have sent their email to the disposable address. That is clear context for when to use it, but there is no guidance on what to do if the email has not yet been sent or on any alternative tool for related diagnostics.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the description isn't needed to establish the safety profile. It nonetheless adds real behavioral context: SSRF hardening, private ranges blocked, HTTPS-only, and per-hop validation, which tells the agent what inputs will be rejected and that the fetch happens out-of-band from the caller. It stops short of mentioning rate limits, auth, or timeout/error behavior.

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 front-loaded sentences: the capability first, then flags and security constraints. It is dense but every clause carries information; the trailing 'how it works' documentation link is slightly promotional but low-cost given the SSRF claim it substantiates.

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 read-only tracer with no output schema, the description covers what it does, what it returns (per-hop status, IP, TLS, timing, flag categories), and the security envelope it operates in. Nothing an agent needs in order to call it correctly appears to be 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?

There is a single required parameter at 100% schema description coverage ('Absolute http:// or https:// URL to trace'), so the schema already carries the semantics and the baseline is 4. The description reinforces that the URL is fetched rather than returned, but adds no format or syntax detail 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?

A specific verb plus resource: 'Follow a URL server-side through every HTTP redirect hop to its real final destination,' with explicit scope (server-side, every hop). It also names the artifacts returned (per-hop status, IP, TLS, timing, flags), which distinguishes it cleanly from the other siblings, all of which are mail/DNS/reputation tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The use case is implied by the scope statement (resolve where a URL really lands, including meta/JS redirects), but there is no explicit when-to-use or when-not-to-use guidance, no stated prerequisites, and no alternative named. The sibling list contains no competing URL-fetching tool, so the lack of routing is a minor rather than serious gap.

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, so safety and external-dependency behavior are covered. The description adds the shape of the result, but says nothing about registry rate limits, thin-registry/partial results, or failures for unregistered domains, which matter for an open-world lookup.

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 identifying purpose and payload with no filler. Every clause earns its place by naming a returned field.

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 the returned fields, which is the main completeness burden here. It falls short only on edge-case behavior (unregistered domains, rate limiting) that an agent calling an open-world WHOIS service would benefit from knowing.

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 with 100% schema description coverage, so the schema already carries the meaning. The description adds nothing about domain syntax or whether IDNs/subdomains are accepted, 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?

Names a specific resource (domain) and enumerates exactly what the summary contains: registrar, created/updated/expires dates, nameservers, DNSSEC, status flags. It does not, however, contrast itself with siblings such as get_domain_age, which covers an overlapping concern.

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 statement of when to use this versus alternatives, no prerequisites, and no exclusions. An agent can infer it is a per-domain lookup from the name, but nothing routes it away from get_domain_age or check_spoofability.

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