harborrank

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

Annotations already establish readOnly/openWorld/non-destructive safety, so the description only needs to add context. It does, usefully: it discloses the data provenance (GA4's AI Assistant channel plus referrer matching) and notes it covers assistants and history the built-in channel misses. It omits auth/rate-limit behavior, but the sourcing detail is genuine added value.

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

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

A single dense paragraph that is front-loaded with the core purpose and then layers scope, sourcing, and use cases. Nearly every clause earns its place, though the provider list and closing tips make it longer than strictly necessary.

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

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

With an output schema present, the description need not explain return values, and it supplies scope, data source, differentiating coverage, and usage intent. An agent has everything needed to select and call this tool correctly, including the required projectId pointer via list_projects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description references compareTo and the landing-page split, and clarifies what metrics surface (revenue per assistant, AI's share of all traffic), but the parameter-specific semantics (formats, enums, defaults) already live in the schema, so this adds only marginal meaning.

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 (measure) and resource (AI assistant referral traffic) with named scope: sessions, engagement, key events, revenue per assistant. It is unmistakably distinct from broad siblings like get_analytics_report or get_landing_page_performance because it names the AI-assistant channel and its providers.

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 concrete usage contexts — prove AI-search visibility pays off, track growth with compareTo, and pick pages to optimize — which tells the agent when this tool is the right pick. It stops short of naming an alternative tool or an explicit when-not condition against get_analytics_report.

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 safety and data-source scope are covered structurally. The description adds the prerequisite that a GA4 property must be connected to the project and that comparisons can be requested, but says nothing about rate limits, quota, or what happens when no property is connected. Adequate but not rich beyond 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 sentences, front-loaded with the resource and scope, then usage guidance, then sibling routing. Only mild filler ('This is what happens after the click') and every sentence carries routing or semantic value, so it is appropriately sized.

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 11 parameters, full schema description coverage, an output schema, and read-only annotations, the description supplies the intent, routing and prerequisite context an agent needs to select and call it. It does not need to explain return values, and the remaining gap (connection/auth failure behavior) is minor.

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 every parameter including compareTo, rowLimit, filters and dimensions is already documented with examples in the schema. The description restates the breakdown dimensions and period-over-period comparison but adds no syntax or constraint detail the schema lacks, making 3 the correct baseline.

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

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

States a specific verb and resource ('Query the project's connected Google Analytics 4 property') and enumerates the exact metric families (sessions, users, engagement, key events, revenue) and breakdown dimensions, so an agent can tell it apart from get_search_console_performance or get_landing_page_performance without opening the 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 frames when to use it ('what happens after the click — see which traffic actually converts, explain traffic drops, back recommendations with business outcomes') and names two alternatives with the condition that selects each: get_search_console_performance for the before-click half, get_landing_page_performance for the joined view.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real behavioral value beyond that: the join semantics across two data sources, the degraded mode without Search Console, and diagnostic flags such as clicks Analytics never records. It does not mention auth, rate limits or pagination, but the additions are meaningful.

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?

Opens with the core operation and keeps the value proposition front-loaded. The remaining sentences each carry distinct diagnostic or use-case information, though the description is dense and runs long relative to what most agents need to disambiguate the call.

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 an output schema present, return values need not be explained, and annotations cover the safety profile. The description supplies the join behavior, the fallback condition, and the intended analytical scenarios, leaving no essential gap for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters (dateRange enum, startDate/endDate, pathContains, rowLimit, projectId) are already fully documented in the schema. The description adds no parameter syntax or format detail beyond what is structured, making the baseline 3 appropriate.

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

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

States a specific verb and resource and pins down the scope precisely: per-page SEO funnel joining Search Console clicks/impressions/position with Analytics sessions, engagement, key events and revenue. This clearly distinguishes it from siblings like get_search_console_performance and get_analytics_report, which each cover only one half of the join.

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 when-to-use context ('best starting point for SEO prioritization, content audits and client reporting') and names concrete analytical intents. It also discloses a degraded operating mode ('works with Analytics alone if Search Console isn't connected'). It stops short of naming the sibling alternatives it competes with, so it is not a full when/when-not/alternatives treatment.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds meaningful behavior beyond them: you cannot pay on the user's behalf, payment is by card or PayPal, and whoami should be called afterward to confirm. It stops short of describing output/pagination, but the added context is substantial.

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

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

Front-loaded with the return value, then usage triggers, then the human-in-the-loop constraint, then the verification step. Every sentence carries a distinct instruction and none is wasted.

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 an output schema present, return-value detail is not needed, and annotations cover the safety profile. The description fully covers when to call it, what the agent can and cannot do, and what to do afterward.

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 single 'plan' enum parameter is already fully documented ('omit to get a link for every paid plan'). The description's 'a checkout link for each' corroborates but adds no syntax or format detail beyond the schema, matching the baseline 3.

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 ('Returns') and three concrete resources: the user's current plan, the paid plans with price/credits/projects, and a checkout link per plan. An agent can distinguish this from get-analytics or whoami siblings immediately.

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?

Explicit triggers: user asks to upgrade/change plan/buy credits, or a tool reports a needed paid feature or exhausted credits. It also names the follow-up (call whoami after payment) and the flow constraint (the user opens the link themselves).

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to repeat safety. It adds behavioral detail about sorting by listing count, which helps set expectations. No contradictions 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 concise sentences, no fluff, with the core purpose front-loaded and the use case in the second sentence. 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?

Complete for a simple read-only tool. Output schema exists, schema coverage is 100%, and annotations cover safety. The description covers purpose, sorting, and usage context—nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters (limit, query, projectId) are already documented. The description does not add any parameter-specific semantics beyond the schema, which is sufficient per the baseline for full coverage.

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 exactly what the tool does: lists the Google Business category taxonomy, used by prospect_leads' categories filter, and sorted by listing count. This clearly distinguishes it from all sibling tools, none of which handle categories.

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

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

Explicitly states the use case: 'Use to find the right category slugs for a niche.' It implies this is the go-to for category lookup, but does not mention alternatives or when not to use it. Since no other tool deals with categories, the guidance is clear enough.

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 substantial context beyond the annotations: no third-party API, robots.txt-awareness, same-origin scoping, background execution, and honest flagging of blocked pages. This is precisely the operational detail the openWorldHint/readOnlyHint annotations cannot convey.

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

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

A single dense but well-organized paragraph that front-loads the action and then the follow-up flow. Every clause is informative, though the sentence is lengthy and could be split for faster scanning.

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?

An output schema exists, so return values need no explanation; the description instead covers the async lifecycle and the follow-up tools, which is exactly what an agent needs to invoke and complete this workflow correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents url, maxPages, projectId, and runLighthouse. The description reinforces the crawler's scope (robots.txt-aware, same-origin) and the Lighthouse sampling, but adds little parameter syntax or format detail beyond the schema baseline.

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

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

States a specific verb (start/run) and resource (site audit) and details exactly what the crawl checks: broken links, titles, redirect chains, orphan pages, canonical issues, thin content. It clearly distinguishes itself from siblings by routing results through get_audit_status and get_audit_issues.

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 describes the workflow: it runs in the background, so the agent must poll get_audit_status and then read get_audit_issues. It also notes the optional Lighthouse step. It does not clarify when to prefer this over the semantically adjacent sibling inspect_urls, so it stops short of full when/when-not coverage.

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