UK Data: Web research

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

No annotations are supplied, so the description carries the full burden. It does add genuine value by disclosing the credit cost (2 credits) and the breadth of the returned report, and "check" implies a read-only operation. It stops short of describing failure modes: no word on timeouts, unreachable URLs, JS-rendered pages, or whether redirects are followed or merely reported.

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: purpose first, then the enumerated checklist, then cost in parentheses. The long comma list of checks is bulky but every item informs the agent about coverage. Minor cost: the sentence is dense for a single-line description.

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 tool with no output schema, the enumeration of inspected elements effectively substitutes for a return-value description, and the cost note covers billing behavior. What remains thin is operational context — expected latency, error handling, and how the "list of issues" is structured.

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

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

There is a single `url` parameter and schema coverage is reported at 100%, so the baseline is 3. The description only restates that the input is "a URL" of the page being checked; it adds no constraints on format (scheme required? absolute only?), query strings, or authenticated pages.

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 ("On-page SEO check of a URL") and then enumerates exactly what is inspected: title, canonical, robots, hreflang, Open Graph, structured data, headings, alt text, redirects, word count, issues. An agent can distinguish this from sibling checkers such as domain_check, ssl_check or vuln_check because the scope is explicitly on-page content rather than domain/DNS/security posture.

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 by the scope phrase "On-page SEO check" — an agent can infer this is the tool for auditing a page's SEO metadata. However, there is no explicit when-to-use/when-not guidance, no mention of alternatives (domain_check, read_url, ssl_check) and no note on prerequisites such as whether the URL must be publicly reachable.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses the source (Internet Archive) and cost (1 credit), but does not state that it is read-only, how errors or rate limits behave, or what the monthly list 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?

The description is compact and front-loaded: the main purpose comes first, followed by the source and cost. Every element earns its place with no redundant wording.

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 four-parameter tool with no output schema, the description covers the main modes and cost adequately. However, it omits limit semantics, default date behavior, and details about what a monthly list returns.

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 meaning by clarifying that date is the target date and list produces a monthly list of snapshots, but it does not explain the limit parameter or default behavior.

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 outcome: the closest archived snapshot of a URL to a date, or a monthly list of snapshots. It is clear what the tool returns, though it does not differentiate itself from siblings such as read_url.

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 implies two modes through the mention of a closest snapshot and a monthly list, but does not explicitly say when to choose list mode versus snapshot mode. There are no exclusions or named alternatives.

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?

No annotations are provided, so the description must carry behavioral context. It discloses the data source, example returned facts, and a 1-credit cost, but does not state read-only intent, rate limits, ambiguity handling, or error behavior; adequate for a simple lookup, but incomplete.

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 front-loaded sentence with a compact fact list and cost. There is no filler, and every element is useful for selection.

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 lookup, the description gives enough to understand the returned fact categories. However, it lacks input guidance for choosing between id and query, and with no output schema it only lists examples rather than explaining the returned structure.

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 parameters. The description adds entity-type context but does not clarify the relationship between the id (Q-id) and query parameters, nor what query accepts, so it only meets the 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?

The description identifies the data source (Wikidata), the entity types (company, person, place), and concrete fact categories such as headquarters and CEO. It is clear what the tool retrieves, though it does not explicitly mention lookup by Q-id or name.

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 phrase 'structured facts' implies use when structured entity data is needed, but there is no explicit when-to-use or when-not-to-use guidance. It also does not mention alternatives such as wikipedia_summary or company_profile, so the agent must infer when this tool is preferable.

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