AEO Backlink

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine value by disclosing the return shape (counts, dates, bounded records, direct links), but says nothing about behavior for URLs with no snapshots, rate limits, or pagination beyond the bound — relevant gaps given openWorldHint implies external dependency.

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 resource, followed immediately by the enumerated outputs. Every clause carries information; nothing is padding.

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 only two parameters and no output schema, the description correctly compensates by describing the return payload in detail. It stops short of covering empty-result or error behavior for unarchived URLs, which an agent would benefit from knowing before calling.

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 'url' and 'limit' are already documented with format and bounds. The description's 'bounded list' phrase loosely correlates with 'limit' but adds no syntax, default, or semantics 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 ('Return') and resource ('Wayback Machine timeline for a URL'), then enumerates exactly what it yields: total snapshots, first/last archived dates, and bounded snapshot records with archive links. That precision makes it trivially distinguishable from siblings like verify_page_links or find_mentions, which act on live pages rather than archived history.

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

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

There is no explicit when-to-use or when-not-to-use language, and no sibling is named as an alternative (e.g., verify_page_links for live link checking vs. this for historical snapshots). Usage is only implied by the purpose statement itself, which is the definition of a 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?

Annotations already declare readOnly, idempotent, non-destructive, and openWorld, and the description is consistent with that profile (it does network fetching). It adds real value beyond annotations by disclosing that de-obfuscated emails and mailto links are resolved and naming the six platforms covered, though it says nothing about failed fetches, empty results, or rate/robots constraints.

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 action first and the extracted entity types enumerated in a compact parenthetical; no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates what comes back (emails, de-obfuscated variants, mailto links, social handles), which is the right compensation. It stops short of describing result shape (e.g., per-field lists or null handling) and edge-case behavior when nothing is found.

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 'url' parameter, so the schema carries the semantics and baseline is 3. The description only implies that the URL is a page to be fetched, adding marginal detail beyond the schema's own description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ('Fetch a page and extract') with an enumerated resource set: emails (including de-obfuscated and mailto) and handles from six named social platforms. An agent knows exactly what this produces and can distinguish it from sibling tools like find_mentions or find_prospects.

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 'Fetch a page' framing implies usage context (you have a URL and want contact data), but there is no explicit when-to-use/when-not guidance and no routing against siblings such as find_prospects or find_mentions. Usage must be inferred.

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?

Adds real behavioral detail beyond the annotations: results are de-duplicated by host, the competitor's own domain is excluded, and output is approximate rather than exhaustive. That accuracy caveat is exactly the kind of context annotations (readOnly/idempotent/openWorld) cannot convey. No mention of rate limits or how many DDG queries are issued.

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 with the capability front-loaded and the caveat following. 'Free' appears twice and the closing 'free, directional starting point' partially restates the second sentence, which is mild redundancy but not enough to obscure the message.

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 two-parameter read-only lookup with no output schema, the description covers mechanism, accuracy expectations, and result shaping (host dedupe, domain exclusion). It leaves the shape of a returned 'source' entry unstated, which is the remaining gap given there is no output schema to lean on.

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 are already documented in the schema. The description reinforces that the target is a competitor domain and that results collapse to host level, but adds nothing about the limit parameter or accepted URL forms beyond what the schema states. 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: approximating pages that link to a competitor, and names the signal source (free DuckDuckGo domain/brand mentions). The 'approximate'/'directional' framing implicitly separates it from verify_page_links and find_mentions, though no sibling is named explicitly.

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

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

Gives clear context for when to reach for this tool: a free, directional prospecting starting point, explicitly 'not a complete backlink index'. It never names an alternative tool for when authoritative backlink data is required, so the routing is implied rather than explicit.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds that results come from DuckDuckGo HTML and that classification is conditional on the domain argument. It does not mention rate limits, empty-result behavior, whether 'unlinked' requires verification, or what an individual mention contains.

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 dense sentences with no filler; the core action and source are front-loaded and the second sentence conditions the classification behavior on the optional domain argument. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description would ideally sketch what a returned mention looks like (URL, title, snippet, classification flag). The linked/unlinked labeling concept is conveyed, which is the key output concept, so it is nearly complete for a three-parameter read-only search tool.

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 all three parameters are already documented, including the domain's classification role. The description reinforces the optional-domain behavior but adds no syntax, format, or edge-case guidance (e.g. scheme/www handling, behavior when domain matches nothing) 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 ('Find linked and unlinked mentions of a brand') and names the underlying source ('DuckDuckGo HTML results'), which tells an agent this is a web-wide scrape rather than an internal crawl like verify_page_links or find_competitor_link_sources. It stops short of explicitly contrasting itself with those siblings, so a 4 rather than a 5.

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

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

Usage is implied rather than stated: the reader can infer this is the discovery tool for brand mentions and that supplying 'domain' unlocks the linked/unlinked split. There is no explicit when-to-use/when-not and no named alternative (e.g. find_competitor_link_sources for competitor domains).

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description still adds real behavioral value by disclosing the data source (DuckDuckGo) and the merging-by-host dedupe behavior, and it frames the three outreach angles that drive result volume. It omits latency, rate-limit, or result-quality caveats for an open-world search.

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 that front-loads the verb and the resource types, then packs mechanism and merge behavior into a subordinate clause with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only two fully documented parameters, full annotations, and no output schema, the description covers what the tool does and how results are consolidated by host. It leaves the shape of returned prospects (fields, counts) unspecified, which is a minor gap given no output schema exists.

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 baseline would be 3, but the description earns extra credit by naming the three outreach angles, which makes the 'per outreach angle' semantics of limitPerAngle concrete rather than abstract. It still says nothing about topic formatting or what a larger limit costs.

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 (find), a specific resource (guest-post, resource-page and roundup link-building prospects), and the mechanism (outreach footprints via DuckDuckGo merged by host). It is clearly distinct from most siblings, though it never explicitly contrasts with the near-neighbour find_competitor_link_sources, leaving that differentiation to inference.

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 description makes it clear the tool is for topic-driven prospecting by footprint, but it never states when to prefer it over find_competitor_link_sources or find_mentions, nor any prerequisites or exclusions.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety bar is low, yet the description still adds real value: it names the return shape (subject line and body) and discloses the BYOK key handling — request-scoped, never persisted or logged. That's meaningful context beyond the annotations. It stops short of describing provider-side failure/rate-limit 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?

Three tight sentences, front-loaded with the action and inputs, followed by the return value and the security guarantee. No filler; every sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly supplies the return shape (subject + body) and the key-handling guarantee, and hints at brevity via 'short'. It leaves out error/fallback behavior across the five providers and any length or rate constraints, so it's strong but not exhaustive for a 7-param, nested-schema tool.

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 71%, so the schema already documents most parameters (contact fields, context.tone/notes/reason, provider enum, apiKey). The description only restates the contact/context framing and the apiKey scoping, adding little for model, provider, maxTokens, or temperature. 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 ('Draft a short, personalized cold outreach email') and names the exact inputs (contact + context) and output (subject line and body). It doesn't need sibling differentiation since no sibling generates content, but it also makes no explicit contrast with extract_contact_info or find_prospects, which would have earned a 5.

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

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

The description implies the use case (cold outreach with a personalized angle) but gives no explicit when-to-use/when-not guidance, no prerequisites beyond BYOK, and no pointer to any alternative tool. An agent must infer that it should gather contact/context data from the sibling tools first.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely new behavior: it performs a live network fetch and returns anchor text, rel attribute values (nofollow/sponsored/ugc) and a dofollow verdict. It stops short of disclosing failure modes (unreachable page, timeouts, redirects) or how multiple matching links are handled.

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 that front-loads the action and then the reported fields; every clause carries distinct information and there is no filler or repetition of 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?

With only two parameters and no output schema, the description's job is to convey what comes back, and it does – anchor text, rel tokens, dofollow status. It is slightly thin on negative outcomes (no link found, page blocked/unreachable) which matter for a live-fetch tool.

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 'url' and 'targetDomain' are already documented with format and example. The description restates them at a high level ('a page', 'target domain') without adding matching rules, subdomain handling, or normalization semantics. 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 ('fetch a page and confirm whether it contains a link to the target domain') plus the exact outputs ('anchor text and rel attributes... whether the link is dofollow'). No sibling (check_page_history, find_mentions, find_competitor_link_sources) does live link verification, so the scope is unambiguous without explicit comparison.

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 description – an agent can infer this is for backlink verification, but there is no statement of when to prefer it over find_mentions or find_competitor_link_sources, and no mention of prerequisites or cost (live fetch per call).

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