backlinkmcp-server

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

Annotations already declare readOnlyHint=true and openWorldHint=true, which the description agrees with (an audit is read-only; openWorldHint fits the free/no-LLM-calls claim). Beyond annotations, the description adds valuable behavioral traits: 'Free (no LLM calls)' signals cost/performance characteristics, and the scope disclosure (25 crawlers, /llms.txt, hygiene checks) sets accurate expectations for what the audit covers. No contradiction exists.

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 purpose is front-loaded in the first clause, and the structure flows logically: purpose → consequence framework → scope enumeration → cost signal. Every sentence earns its place. It runs slightly long due to the parenthetical crawler name lists and the em-dash framing, but both carry genuine decision-making value for the agent. Minor trimming possible without losing substance.

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 tool with readOnly/openWorld annotations, this is nearly complete: it explains scope, the decision framework, and cost profile. The only gap is the absence of any description of the output/return format — and since there is no output schema, the description carries that burden entirely. This is a minor omission against an otherwise thorough definition.

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% — the single 'domain' parameter is fully documented in the schema ('Root domain to audit, e.g. 'yoursite.com''). The description references the site implicitly but adds no parameter-level detail beyond the schema. Baseline 3 is appropriate since the schema already carries the full burden.

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 opens with a specific verb+resource: 'Audit which AI crawlers a site allows or blocks in robots.txt.' It further distinguishes itself by enumerating its exact scope (25 known AI crawlers, /llms.txt existence, robots.txt hygiene), which clearly separates it from the sibling ai_visibility_report and other SEO tools in the list. The purpose is unambiguous and non-tautological.

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 provides strong implied context — it frames the audit around the visibility-vs-training crawler decision, making it clear this is a pre-decision check before blocking or allowing crawlers. However, it never explicitly states when to choose this tool over siblings like ai_visibility_report or site_audit, nor does it name alternatives or exclusions. Usage is inferable but not stated.

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?

This is highly transparent: it discloses that a live multi-model panel runs ('8 models × 3 prompts × up to 4 competitors'), that credits scale with samples, that 'Answer engines are nondeterministic', and that history mode 'Costs no credits.' These details go well beyond the annotations and meaningfully set agent expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and front-loaded: the first sentence captures the core audit purpose, and the following sentences explain modes and cost constraints. Some mode details are repeated in the schema, but the description remains efficient and avoids fluff.

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?

Despite having no output schema, the description clearly enumerates what the report contains: whether the brand gets recommended, share-of-voice, why the leader wins, referring-domain gap, and which domains to target. It also covers mode trade-offs, credit implications, nondeterminism, and sampling guidance, so an agent has enough context to invoke 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?

All 9 parameters already have rich schema descriptions, including enums, examples, credit costs, and defaults, so the description does not need to compensate. The tool description adds useful context like the Pro limitation and the referring-domain-gap diagnosis, but schema coverage is 100% and carries the parameter-semantics burden.

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 states a precise purpose: an 'AI Visibility / GEO audit' that 'asks a panel of AI models a buyer-intent question' and reports recommendation rates, share-of-voice, the leader's win reasons, and link targets. This clearly distinguishes it from sibling tools like backlinks_for_domain or core_web_vitals, which address different SEO concerns.

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 clear context on when to use each mode ('parametric ... baked-in brand memory' vs 'retrieval ... live web-search models'), and flags that the tool is 'Pro plan only' and spends credits. It does not explicitly name sibling alternatives or state when not to use it, but the use case is well-scoped enough for an agent to route correctly.

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 signal readOnlyHint and openWorldHint, and the description adds useful behavioral context: the returned payload composition and the row limits by tier. It does not mention pagination or sorting, but the disclosed details go beyond the structured annotations.

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 carry the core output description, tier limits, and a pointer to an alternative tool. The most identifying information is front-loaded, and there is 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 adequately explains what the caller will receive: total inlink count and a ranked list with authority and outbound link counts. The tier limits add practical context, though sorting or field names are not specified, which is a minor gap for a single-parameter read 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?

The schema already fully documents the single 'domain' parameter with an example ('stripe.com'), so schema coverage is 100%. The description adds no additional parameter-level semantics beyond restating that it operates on a domain.

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 action and resource: 'Full backlink payload for a domain' with concrete content ('total inlink count plus the ranked list of linking domains'). It also distinguishes itself from the sibling domain_authority_score by noting that tool covers only the headline number.

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 explicitly provides an alternative: 'use domain_authority_score for just the headline number.' It also sets expectations around tier-based row limits, helping the agent decide whether this tool is appropriate for the user's plan.

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 mark readOnlyHint and openWorldHint. The description adds meaningful behavioral detail: threshold of linking to MORE THAN ONE domain, domain-level aggregation with no per-link URL/anchor, and free/Pro row and domain-count limits. No contradiction with annotations.

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 core function before limits/marketing framing. Each clause earns its place: definition, ranking, use case, granularity, and tier constraints.

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 tool, the description fully covers inputs, output shape, ranking, granularity, and result limits. No output schema exists, but the description tells the agent enough to invoke it correctly and interpret results.

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 already documents 'domains' as root domains to intersect with 2-4 values and free-tier behavior. The description reinforces this but doesn't add significant new parameter semantics beyond the schema; 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?

The description opens with a specific verb and resource ('Multi-domain backlink overlap') and precisely defines output: domains linking to MORE THAN ONE of the given 2-4 domains, ranked by overlap then authority. It also differentiates from siblings like top_linkers_for_domain by emphasizing multi-domain intersection rather than single-domain backlinks.

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 use case ('who links my whole niche?') and appropriate scenario (must-have publications/roundups competitors share), which implies when to use this over single-domain tools. It doesn't explicitly name alternatives or state when not to use it, so not 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 mark the tool as read-only, and the description adds useful behavioral detail: it calls Google PageSpeed Insights, returns both Lighthouse lab results and CrUX field data, and notes field data is provided only when available. This goes beyond the bare annotation and helps set expectations for incomplete data.

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 well-structured sentence that front-loads the core purpose, names the specific metrics, and then clarifies the data sources. Every clause adds value 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?

With no output schema, the description helpfully names the expected output components: LCP, INP, CLS, performance score, Lighthouse lab data, and CrUX field data. It doesn't describe the full response shape or error behavior, but for a simple read-only page-vitals tool, this is sufficient guidance 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?

Schema description coverage is 100%, so the schema already documents both 'url' and 'strategy'. The description does not add new semantic detail about parameters, such as URL formatting or how strategy changes the run. Baseline 3 is appropriate because the schema carries the documentation burden.

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 ('Get') with a precise resource: Core Web Vitals (LCP, INP, CLS), a performance score, and the data source (Google PageSpeed Insights). It clearly distinguishes this from the sibling site-audit and backlink tools by focusing on page-level vitals and performance.

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 clearly implies when to use the tool: when a page-level performance score and Core Web Vitals are needed, with the added nuance of both lab and field data. It doesn't explicitly name alternatives or exclusions, but the context is clear enough given the unrelated sibling tools.

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 and openWorldHint, covering the safety profile. The description adds useful behavioral context beyond those: the weighting basis, the proprietary web-scale index source, and the return shape (domain_rating-style score plus referring domain count). No contradiction with annotations.

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 with no filler. The main action is front-loaded, followed by one sentence explaining provenance and return value. Every clause earns its place and the structure makes the tool's purpose immediately scannable.

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 no output schema, the description covers the score's intent, computation weighting, source, and return contents. It is sufficient for an agent to invoke correctly. A minor gap is that the score's scale or range is not specified, but this is not critical for selection and usage as currently specified.

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 parameter is fully documented with type and example ('Root domain, e.g. 'stripe.com''). The description's mention of 'domain' adds no semantic detail beyond the schema, so the baseline 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?

Description clearly states the verb-resource pair: 'Get an editorial-authority score for a domain.' It adds distinguishing detail by explaining the score is weighted toward high-trust wiki/edu/gov/news referrers from a proprietary link index, which separates it from sibling tools that return raw backlink lists or reports.

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 this tool is for holistic authority measurement, but it provides no explicit guidance about when to choose it over siblings like backlinks_for_domain or top_linkers_for_domain. There are no exclusion criteria or alternative routing cues. The context is clear only in a general sense.

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 readOnlyHint and openWorldHint annotations, the description discloses significant behavioral limitations: domain-level only, no per-link URLs or anchor text, each row is a domain rather than a confirmed link, noise filtering, and free/Pro tier caps. This is exactly the kind of beyond-schema transparency that prevents misinterpretation.

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 longer than average but every sentence carries distinct information: the gap definition, domain-level limitation, filtering behavior, and tier limits. It is front-loaded with the primary purpose and avoids filler, though it could be slightly tightened without losing value.

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 the tool has no output schema, the description does a good job explaining what the result will be: domains ranked by authority, not URLs or anchor text. It also covers tier limits and input constraints. It could add a little more about the exact output shape or ranking metric, but it is largely complete for invocation decisions.

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 is 3. The description adds useful meaning by explaining that 'domain' is YOUR site, 'competitors' are root domains to mine, and that the free tier uses only the first competitor. This adds real value beyond the raw schema descriptions.

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: competitor backlink-gap analysis that returns domains linking to competitors but not to you. It clearly distinguishes itself from siblings like backlinks_for_domain or top_linkers_for_domain by emphasizing the 'NOT to you' gap angle and 'warm outreach shortlist' purpose.

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 explicitly states when to use the tool: when you want domains that link to competitors but not your domain for link building outreach. It does not explicitly name sibling alternatives, but it gives clear context, input expectations, and tier-based behavior that helps an agent decide suitability.

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?

It goes well beyond the readOnlyHint and openWorldHint annotations by disclosing that results are domain-level heuristics, not confirmed toxic links, that no per-link URL/anchor data is provided, and that each row is only a candidate for review. The Google disavow caution further clarifies the intended non-destructive usage. This is rich behavioral context that materially changes how an agent would use the result.

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 dense but purposeful: it front-loads the core action, then limitations, then safety guidance, then quotas. Each clause earns its place, though the first sentence is long and packed. No filler or repetition, and it remains readable despite its richness.

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 one parameter and no output schema, the description covers the key contextual needs: what the tool returns (domain rows, not links), which heuristics are used, what is intentionally omitted (per-link URL/anchor), account limit differences, and the disavow caution. It does not describe the exact return fields or pagination, but for a single-parameter heuristic audit tool this is near-complete.

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 fully documents the single 'domain' parameter. The description adds a little context by calling it a domain's linkers, but doesn't add new parameter-level detail beyond what the schema provides. A baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 states a specific verb and resource (scans a domain's linkers, flags spammy disavow candidates) and lists concrete heuristics (abused TLDs, spam keywords, hyphen/keyword stuffing, outbound counts). It also explicitly distinguishes itself from the sibling tool find_link_prospects by calling itself 'the inverse', making its position among siblings unmistakable.

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

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

The description names an alternative (find_link_prospects) and clarifies when not to use this tool ('use this to audit, not to auto-disavow'). It also implies the primary use case: reviewing domains flagged as toxic linker candidates. It doesn't explicitly contrast against other sibling tools like common_linkers or top_linkers_for_domain, so a small gap remains.

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 readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds value beyond annotations by clarifying that the key must be hosted and controlled by the user, and by stating the intended effect (near-instant indexing by Bing and Yandex). No contradiction with annotations.

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 with no wasted words. The core action and purpose are front-loaded, and the critical prerequisite appears immediately after. Every clause contributes necessary 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?

For a simple two-parameter mutation tool with idempotent and non-destructive annotations and no output schema, the description provides sufficient context: target service, key prerequisite, and purpose. Minor gaps like response handling and same-host constraint exist, but the latter is already in the schema.

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 fully documents both parameters. The description reinforces the key-hosting requirement and supports one-or-many URLs, but adds no additional format or syntax details beyond the schema. 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 ('Submit') and resource ('URLs to IndexNow'), names the search engines (Bing, Yandex), and clearly distinguishes itself from the unrelated sibling SEO tools. No ambiguity about what this tool does.

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?

Clear use case: submit URLs for near-instant indexing. The description provides a necessary prerequisite (hosted key) and explicitly notes the tool does not create the key, helping the agent decide whether it can use the tool. No explicit alternatives are named, but no sibling tool competes with this functionality.

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=true, so the description does not need to restate safety. The description adds behavioral detail beyond the annotations: it validates JSON syntax, flags missing recommended fields, and specifically targets JSON-LD rather than all structured data formats. This gives the agent a useful model of what the tool will and will not do.

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 compact sentences with no filler. The primary action is stated first, followed by the specific validation behavior and supported types. 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?

For a simple one-parameter, read-only, no-output-schema tool, the description covers the input, the operation, the validation checks, and the relevant schema.org types. It does not describe the exact return format, but the description implies a validation result and flags, which is sufficient for an agent to select and invoke the tool 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?

The only parameter, url, is fully described in the input schema ('Full page URL to check for structured data'). The description adds no additional parameter-level meaning, but with 100% schema description coverage, the schema carries the semantic burden adequately.

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 states a specific verb+resource: it extracts and validates JSON-LD structured data (schema.org) from a page. It also names concrete checks (JSON validity, missing recommended fields) and lists the supported schema.org types, making it clearly distinct from the broad SEO audit and link-analysis 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 establishes a clear context: use this when you need to check a specific page for JSON-LD structured data and validation issues. It does not explicitly name alternatives or state when not to use it, but the focused scope ('from a page', JSON-LD only) is enough to guide selection among the mostly unrelated sibling tools.

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?

The description discloses that the tool fetches the URL and returns a list of concrete issues, which complements the readOnlyHint and openWorldHint annotations. It clearly identifies it as a non-mutating, live-fetch operation without contradicting the annotations.

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 with the core action and resource, followed by a concise checklist of audited signals and a clear return type. Every sentence earns its place without redundancy or 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-only tool, the description provides sufficient context: what it fetches, what signals it checks, what it returns, and its scope limitation. Even without an output schema, an agent can invoke it correctly and understand the result shape.

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 documents the url parameter with a full URL example. The description adds value by clarifying the URL must be a single page rather than a domain or site root, reinforcing the parameter semantics 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 uses a specific verb ('Fetch a page and audit') and names concrete on-page SEO signals, making the tool's function unmistakable. The final sentence explicitly distinguishes it from a site crawl, which separates it from sibling tools like ai_crawler_audit.

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 clearly states that this tool handles a single page, not a site crawl, giving a useful exclusion for selection. It could be stronger by naming an alternative tool for site-wide audits, but the context is clear enough for an agent to decide when to use it.

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, so the safe read nature is covered. The description adds useful behavioral detail beyond annotations: the fixed limit of 25, the ranking criterion based on the linking domain's authority, and that link counts are included. This gives an agent a clear picture of what the call will return.

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 with no filler. The first sentence front-loads the functional behavior, and the second provides a practical use case. Every word 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 one simple parameter and no output schema, the description fully explains what the agent gets back: top 25 linking domains, ranking basis, and link counts. Nothing needed for correct invocation or interpretation 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% and the single 'domain' parameter already has a clear example. The description adds no additional semantic detail about parameter formatting or normalization, so it stays at the baseline for well-covered schemas.

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 the exact operation ('Return'), the resource ('top 25 domains linking to a given domain'), the ordering ('ranked by the linking domain's own authority'), and the included metric ('link counts'). This clearly distinguishes it from sibling tools like backlinks_for_domain, which would focus on individual backlinks rather than ranking linking domains.

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?

Provides clear usage context by positioning the tool as 'good for a quick competitive/backlink-profile skim.' It does not explicitly name alternatives or say when not to use it, but the use case is specific enough for an agent to select it appropriately among the siblings.

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 annotations by explaining the live-fetch behavior, the homepage-only scope, and the semantics of 'not_found.' This aligns with and reinforces readOnlyHint and openWorldHint. It gives the agent exactly the nuanced behavioral context needed to interpret results correctly.

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 action leads, the operational caveat follows, and the default behavior closes. Every sentence earns its place and nothing is redundant with the title or schema.

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 tool with three parameters and no output schema, the description provides strong behavioral and interpretive detail. The only notable gap is that it never outlines the response shape or fields returned for each linker, leaving the agent to infer output structure from the 'not_found' hint.

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 all three parameters. The description reinforces the default 'top 8' and max of 15, but adds no meaningful parameter semantics beyond what the schema already provides.

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 action: live-verify backlinks by fetching linking domains' homepages and confirming an actual href. It clearly differentiates from index-based sibling tools like backlinks_for_domain by emphasizing 'RIGHT NOW' and 'real-time proof.'

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 a clear use context: it complements the index with real-time proof. It also provides an important interpretive caveat about 'not_found' meaning only 'no link on the homepage today.' It stops short of explicitly naming sibling alternatives or stating when not to use the tool, so it is not a 5.

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