fabricate

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds topical scope about permissions and signed-in workflows, but does not describe operational behavior such as return format or side effects. With annotations carrying the safety burden, this is a modest contribution.

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 efficient sentence fragment with no wasted words. It is appropriately sized, though slightly terse as a fragment rather than a complete statement of purpose.

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 zero-parameter, read-only tool with no output schema, the description provides thematic coverage but stops short of saying what is actually returned (e.g., a guide document) or how it relates to sibling read/search tools. It is minimally adequate but leaves a clear gap in return semantics and usage context.

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 tool takes zero parameters and schema coverage is 100%, so the baseline is 4. The description does not need to explain parameter syntax, and it adds no misleading parameter information.

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 lists content topics (public access, signed-in workflows, permissions, referral attribution) but never states a clear action or return type. It is not a tautology of the name, but an agent cannot tell whether it retrieves a guide, performs an access check, or does something else. It also does not distinguish itself from siblings like fabricate_read_page or fabricate_search_pages.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as fabricate_read_page or fabricate_search_pages. The description gives topics but does not help an agent decide in which context this tool is the right call.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. Beyond that, the description adds useful content-level disclosure — that values are USD-denominated and sourced from billing configuration — which matters because there is no output schema to convey return shape. It does not, however, mention auth/permission requirements or caching/refresh behavior.

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

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

A single front-loaded sentence with no filler; every clause (plans, USD prices, monthly credits, per-generation limits, billing config source) carries information about the return 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?

With no parameters, no nested objects and no output schema, the description's enumeration of returned fields is the main thing an agent needs, and it is present. Minor gaps remain around freshness of billing data and whether the response is a single plan or a list, but nothing essential is absent.

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 tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate. No parameter claims in the description contradict the empty 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?

Specific verb (get) plus a named resource (Fabricate plans) with an explicit enumeration of the payload: prices in USD, monthly credits, per-generation credit limits. This is unmistakably distinct from its siblings (agent guide, page reading, page search), so an agent can select it without inspecting 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 implies when the tool is useful (whenever the agent needs plan/pricing/credit information), but it never states that explicitly nor names when to prefer it over alternatives. For a zero-parameter, sole-purpose info tool the implied usage is reasonably obvious, so a middle score fits rather than a low one.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds value beyond them by disclosing the return format (Markdown) and the scoping constraint (canonical public pages only), which is not in any structured field; error behavior for invalid paths is 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?

Two short sentences, purpose first, input sourcing second, with zero filler and a concrete example inline.

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 tool with full annotations, the definition covers purpose, input source and output format despite there being no output schema. It omits what happens on an invalid or non-canonical path and whether long pages are truncated, which are minor for this 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 has 0% description coverage for the single 'path' parameter, so the description must compensate, and it does: it states the expected format with a concrete example ('/pricing') and its provenance. It could have noted the 200-character limit or casing rules, keeping it from a 5.

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

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

Specific verb+resource: reads a canonical public page and states the output format (Markdown). It explicitly ties itself to the sibling fabricate_search_pages as the source of valid paths, so an agent can route between the two without opening either 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?

Gives clear usage context: the path must come from fabricate_search_pages, which effectively tells the agent to search before reading. No explicit when-not-to-use or failure conditions are given, so it stops short of 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 declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so safety and determinism are covered. The description adds the useful scope fact that only public canonical pages are indexed and private apps/account data are excluded, which is not in the annotations. It does not describe result format or ranking behavior.

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

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

Two short sentences with zero filler, and the core action is front-loaded before the scope exclusion. Nothing is redundant.

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 should say more about what a result looks like and how many are returned, but it only names the resources. For a 2-parameter read tool the essentials (what it finds, what it excludes) are present, making it adequate but with a clear gap around the undocumented limit parameter.

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 0% for both parameters, so the description carries the burden. It clarifies that 'query' matches against URL keywords, but the 'limit' parameter (default 10, max 25) is never mentioned, nor is the 200-character query cap or what happens when keywords don't match.

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

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

States a specific verb and resource ('Find canonical public Fabricate pages') and adds the matching dimension ('by URL keywords'), so the agent knows what is returned. It does not explicitly contrast itself with siblings like fabricate_read_page or fabricate_get_plans, but the verb/resource pair is unambiguous.

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 a negative scope note ('No private apps or account data') but no positive guidance on when to choose this tool over fabricate_read_page or fabricate_get_agent_guide. No prerequisites or follow-up flow are described, leaving routing to inference from the tool name alone.

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