SEO Data MCP (SteadyScrape)

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

Annotations already declare read-only, idempotent, non-destructive behaviour, so the description's job is to add operational context — and it does: 'strongest first' ordering, a 100-row ceiling, inclusion of target totals, and per-call billing with data. What's missing is whether results can be paged beyond the cap, which matters for a capped 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?

Three compact sentences with zero filler: what it returns, how much, and what it costs. The resource definition and ordering are front-loaded before the limit and billing details.

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

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

With no output schema, the description carries the burden of describing returns, and it does so by listing the row fields plus target totals. The billing disclosure fills a gap annotations can't cover; only the absence of any pagination/cap-escape note keeps it from full marks.

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 parameters are documented in structured form; the description nonetheless adds semantics the schema lacks, namely that results are ordered by link strength and that totals accompany each page of rows. The dofollow field is echoed from the schema but the ordering/ranking semantics are genuinely additive.

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 concrete resource (backlinks or referring domains for a domain/page URL) and enumerates the returned fields, so an agent knows exactly what data comes back. It does not explicitly contrast with adjacent siblings like domain_overview or ranked_keywords, but the resource is specific enough that confusion is unlikely.

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 'backlinks or referring domains' phrasing implies mode selection but never states when to choose one mode over the other, nor when to use this tool instead of domain_overview or ranked_keywords. Usage is implied rather than directed.

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 establish read-only, idempotent, non-destructive, open-world behavior, so the description's added value is the billing rule ('billed per started block of 10 domains that have data') and the data-source scope (Google, one country). It does not cover throttling, partial-data handling, or whether domains without data still consume the block.

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 sentence with zero filler, front-loaded with the batch limit and payload scope. The colon-separated metric list is slightly run-on but every item earns its place because it defines the payload.

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 aggregate lookup with no output schema, the description supplies the metric set, billing model, and geographic scoping needed to call it correctly. The remaining gap is input formatting of domain strings and behavior on domains with no data.

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?

Country and language are already documented in the schema (67% coverage); the description usefully restates the 100-domain cap and the 'one country' scoping. However, the undocumented 'domains' array remains ambiguous in both places — it does not say whether entries should be bare domains or full URLs, or whether subdomains are accepted.

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 resource (domain-level SEO overview) and enumerates exactly which metrics come back: organic traffic, ranking keywords, paid keywords, domain rank, backlinks, referring domains, spam score, first seen. That makes it distinguishable from narrow siblings like backlinks or ranked_keywords, though it never names an alternative 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?

Usage is only implied: the aggregate metric list plus the 'up to 100 domains' batching hint at bulk overview lookups, while the siblings (backlinks, ranked_keywords, keyword_metrics) suggest the detailed single-metric alternatives but are never referenced. There is no explicit when-to-use / when-not-to-use statement or prerequisite.

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/openWorld/idempotent/non-destructive, so the bar is lower. The description adds genuinely non-obvious context: billing is 'per 10 results of depth', tying cost to the depth parameter, and the schema notes the latency tradeoff. Auth requirements and failure modes are still unstated.

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 compact sentences: what you get, the optional rank-check mode, and the cost model. No filler and the primary purpose is front-loaded.

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

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

With no output schema, the description carries the return-value burden and does so adequately by listing the result fields and SERP feature types. Cost is covered; only edge cases like empty results or error behavior are absent, which is minor for a 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 baseline is 3. The description goes beyond the schema by explaining the outcome of target_domain (that domain's best position, i.e. a rank check) rather than just 'domain to find in the results', and by linking billing to depth.

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 verb+resource ('Live Google organic results for one keyword') and enumerates the returned fields (position, title, URL, domain, snippet) plus SERP features. This clearly separates it from youtube_search and keyword_metrics among the 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 explains the optional target_domain mode ('get that domain's best position (rank check)'), which is real usage guidance for one parameter. However, it never states when to pick this over keyword_metrics or ranked_keywords, nor any exclusions or prerequisites, leaving sibling selection to inference.

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

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, non-destructive), so the bar is lower. The description still contributes the important operational facts: results are normalized 0-100, an average per keyword is returned, and the call is billed when data is returned — a cost signal agents need before invoking. It stops short of noting rate limits or how sparse/short time ranges behave.

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 packs scope, scale, dimensions and the billing caveat with no filler. The primary capability (interest over time) is front-loaded before search-surface and output details.

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?

There is no output schema, and the description carries the return shape (0-100 series plus per-keyword averages), which is exactly what is needed. Defaults for country, time_range and search_type live in the schema, so omitting them here is acceptable. Minor gap: no mention of how the series is sampled or truncated for short time ranges.

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 75%, so most parameters are already documented. The description adds meaning the schema does not: the 0-100 normalization, the effect of comparing several keywords on a shared scale, and the average-per-keyword output. Keywords' max of 5 is restated from the schema, and time_range granularity is left entirely to 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 resource (Google Trends interest-over-time series, 0-100 scale) and its scope (up to 5 keywords, country or worldwide, five search surfaces, plus per-keyword averages). The verb is implicit ('interest over time') but the resource is unmistakable and distinct from siblings like keyword_metrics or google_serp. It does not call out those alternatives by name, keeping it at 4 rather than 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: comparing relative search interest across up to 5 terms in a market. The description gives no explicit when-to-use versus keyword_metrics (absolute volume) or google_serp, and no prerequisites or exclusions. Adequate for an agent that can infer relative-interest comparisons, but routing between this and keyword_metrics is left to guesswork.

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/idempotent annotations, the description discloses the cost model ('billed per started block of 10 keywords that have data') and the partial-failure contract (no-data keywords are returned in noData and not charged). These are operational facts an agent cannot infer from structured fields and directly affect batching decisions.

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 packed sentences with no filler, front-loaded with the returned metrics, then constraints, then billing/exclusions. Every clause carries information an agent would otherwise have to guess.

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?

There is no output schema, and the description compensates by enumerating the returned metric fields. It never states whether results are keyed per keyword or the shape of the noData list, a minor residual gap for a tool with no output 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 country, language and keyword formats are already documented in the schema with defaults and the 1-100 bound. The description restates the 100-keyword/one-country constraint but adds no syntax or format detail beyond it, making the schema baseline of 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+resource: returns Google search volume, CPC, competition, keyword difficulty (with its 0-100 scale), search intent and 12 months of volume. That is far more specific than siblings such as domain_overview or ranked_keywords, so an agent can tell which tool produces keyword-level metrics 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?

The description gives usable context: up to 100 keywords, one country per call, and what happens to keywords lacking data. It does not name an alternative tool or state when a sibling should be preferred, so it stops short of explicit routing guidance.

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, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful behavioral context: billing occurs per call with data, results are capped at 100 keywords per call, and the output is sorted by estimated traffic with position distribution totals.

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 two sentences, front-loaded with scope and return fields. Every sentence carries useful information: the first defines the resource and output columns, and the second adds the per-call limit and billing note.

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 and mentions position distribution totals, billing, and the 100-keyword cap. It is sufficiently complete for an agent to decide and invoke, though it lacks details on empty-result behavior or whether results beyond 100 are accessible via pagination.

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 schema already documents the domain, country, language, and limit parameters with defaults. The description reinforces that domain can be a URL and that results are scoped to one country, but it adds little parameter syntax or meaning beyond what the schema 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?

The description states a specific resource and scope: Google keywords a domain or URL ranks for in one country, sorted by estimated traffic. It clearly distinguishes this from keyword_metrics or google_serp by focusing on domain-ranking keywords, though it does not name sibling tools 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?

There is no explicit guidance on when to use this tool versus alternatives like keyword_metrics, domain_overview, or google_serp. The usage is implied by the description, but no exclusions, prerequisites, or alternative-selection criteria are provided.

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 (readOnly, idempotent, non-destructive, open-world), so the description's real contribution is the cost model — "Billed per 20 results of depth" — plus the 40-result ceiling, which is high-value disclosure an agent cannot get from annotations. It stops short of describing ranking behavior, rate limits, or empty-result handling.

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 tight sentences: the return shape is front-loaded and the limit and billing note follow. Every clause carries information an agent would otherwise have to guess.

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 field enumeration (video ID, title, channel, views, publish date, duration, Short flag) does the work a return-value doc would. The only gap is guidance on query semantics and what happens if fewer than max_results match.

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 75%: country, language, and max_results all carry their own defaults and formats in the schema. The description's "Up to 40 results" merely restates the schema maximum and adds nothing about query syntax, quoting, or locale interactions, 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?

The description gives a specific verb-plus-resource ("YouTube search results for a query") and enumerates the returned fields, so an agent knows exactly what comes back. It does not, however, explicitly contrast itself with the sibling youtube_video, which an agent would need for a detail fetch rather than a ranked listing.

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 youtube_video, google_serp, or google_trends, and no prerequisites or exclusions. Usage is only inferable from the tool name and the "for a query" phrasing.

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 safe-read profile (readOnlyHint, idempotentHint, non-destructive), so the description's main value-add is the billing model: charged per video, transcript billed separately, and transcripts only exist when captions are present. That is meaningful operational context beyond the annotations. Missing rate-limit or quota details 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?

Effectively two sentences, front-loaded with the returned fields and followed by the transcript and billing caveat. There is no filler, and each clause conveys usable 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 read-only fetch tool with complete schema coverage and no output schema, the description does well by enumerating the returned fields and explaining transcript availability. Minor gaps remain around error behavior when no captions exist or language fallback, but the essentials are covered.

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%, with each of the three parameters documented and defaults stated. The description only reinforces the optional transcript behavior and says nothing about the language parameter, so it adds little 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?

States a specific verb-resource pair: 'Public stats for one YouTube video', and enumerates exactly what the stats include. The phrase 'one YouTube video' also separates it from the sibling youtube_search, which searches videos rather than fetching a single video's metrics.

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 makes the use case clear: fetch stats for a known video, optionally with transcript. It does not explicitly name youtube_search as the alternative or say when-not to use it, so it stops just short of full routing guidance.

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