New Site Radar

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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower. The description adds genuinely useful context beyond them: the auth header formats (Bearer nsr_… or x-api-key), a free-tier rate limit of 20 calls/day, and that Pro-only fields are hidden on free keys.

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 listing the payload contents, followed by one compact sentence on auth and tiers. Front-loaded, no filler, every clause carries 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?

With no input params and no output schema, the description carries the interpretive burden and does it reasonably well by naming the content categories and the auth/rate-limit constraints. It could briefly state the return format or whether the response is prose vs structured, but nothing essential 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?

The tool takes zero parameters, so the baseline is 4. The description correctly does not invent parameter semantics, and the auth requirement it mentions is not a schema parameter but is worth surfacing.

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 resource — the methodology behind the boards — and enumerates its contents (data sources, listing thresholds, cross-check bands, confidence and revenue grades, update cadence). This is clearly distinguishable from the sibling data-query tools like get_site or revenue_signals.

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: this is a documentation/explainer tool an agent consults to interpret thresholds and grades. But the description never explicitly says when to call it versus the sibling data tools, nor does it state preconditions beyond the key requirement.

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), and the description adds real behavioral context beyond them: required API key with two accepted header formats, a 20-call/day free quota, and the fact that Pro-only fields are hidden on free keys. It does not say what happens when the domain is not tracked, which 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?

Purpose and returned contents are front-loaded in one dense sentence, followed by the auth/quota sentence. Every clause carries information, though the long comma-separated enumeration of return fields is heavy and slightly hard to scan.

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 correctly compensates by enumerating the returned sections, and it covers authentication and quota. It is nearly complete for a read-only detail tool; only error/empty-result behavior for untracked domains is unaddressed.

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 single 'domain' parameter is fully specified with a regex pattern, maxLength, and an example ('example.ai'). The description adds nothing beyond the schema, so the baseline 3 for high-coverage schemas 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 names the resource precisely ('one tracked site') and enumerates the returned data domains, so an agent can immediately tell this is a full-detail lookup rather than a list. It implicitly contrasts with the sibling search_sites via 'one tracked site', though it never names the alternative explicitly, keeping it short of a 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 only implied: you call it when you need everything about a single site. There is no explicit when-to-use/when-not guidance, no note about first resolving a domain via search_sites, and no mention of behavior for untracked domains. The auth and quota notes are operational context, not selection 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioral context: required API-key auth with both accepted header forms, a concrete rate limit (20 calls/day on the free tier), and the fact that Pro-only fields are hidden for free keys. That is exactly the extra operational detail annotations cannot express.

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?

Purpose and return contents are front-loaded in the first sentence, with auth details following. The auth/rate-limit sentence is dense (two header forms, URL, quota) but every element is actionable information an agent needs to call the tool successfully, so little 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 no output schema, the description must explain return values, and it does (slugs with site counts plus valid filter values). Auth requirements and the free-tier limitation are also covered, leaving nothing an agent needs to invoke it correctly unstated.

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 no parameters and the schema is trivially complete, so the baseline of 4 applies. The filter names listed (type, visits, mom, payment) describe returned values rather than inputs, so they add no parameter meaning but also create no confusion.

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 the concrete resource (category slugs on the current board) and the exact return payload (slugs with site counts plus valid filter values), and it explicitly ties those filter values to the sibling tool search_sites. An agent can distinguish it from get_site or search_sites without opening any 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?

It clearly implies the use case — fetching slugs and the valid values needed before calling search_sites — which is strong contextual guidance. However, it never states this explicitly ('use this before search_sites to resolve filters') nor names any when-not condition, so it stops short of explicit routing.

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 read-only, idempotent, non-destructive behavior, and the description adds genuine extra context: an API key is required, the acceptable header forms (Bearer nsr_… / x-api-key), a rate limit of 20 calls/day on the free tier, and that Pro-only fields are hidden on free. That rate-limit and auth disclosure is exactly the kind of thing annotations don't carry.

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, front-loaded with the data scope and filters before the access requirements. Every clause carries information; nothing is padded or repeated from the 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?

With no output schema, the description usefully flags that field sets differ by tier ('Pro-only fields hidden') and documents auth and rate limits. It could say a bit more about the return shape or ordering, but for a read-only listing tool with full schema and annotation coverage this is nearly 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% — limit (1–50, default 20), since (YYYY-MM-DD pattern), and company (enum of 26 ids) are all fully documented in the schema. The description only restates that company and since exist, adding no syntax or format detail beyond the schema, 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?

It names the resource (AI model releases) and adds meaningful scope: 26 labs, sourcing types (official announcements, blogs, open-weights repos), plus the two filter axes. The retrieval verb is implied rather than explicit, but the resource and scope are unambiguous and clearly distinct from siblings like search_sites or revenue_signals.

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 states that company and since are optional filters, which implies the default is an unfiltered newest-releases feed, but it never says when to reach for this versus another tool or when a filter is expected. No explicit exclusions or alternatives are given.

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), but the description adds real operational context: the required auth header formats, a concrete free-tier rate limit (20 calls/day), and the fact that Pro-only fields are hidden on free keys.

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 returned fields are front-loaded in the first sentence, followed by filters and then auth. It is efficient, though the long auth/rate-limit sentence is somewhat dense and could be split.

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 return values and does so (per-row fields). It also covers filters and auth. Only the ordering/pagination of the 'Top N' results is left implicit.

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 all three parameters are already documented. The description reinforces the category and provider filters but adds no format, range, or default detail beyond the schema, which is the expected 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 states a specific resource (revenue-signals board) and enumerates exactly what each row contains (payment provider, main price, estimated monthly revenue range, grade), which cleanly distinguishes it from siblings like top_rising and search_sites.

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 notes the optional category and payment-provider filters, giving implied usage, but never says when to prefer this over search_sites or top_rising, nor what conditions select the alternatives. Usage is inferred rather than 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?

Goes well beyond the readOnly/idempotent annotations by disclosing the auth requirement, both accepted header formats, the exact free-tier rate limit (20 calls/day), and that Pro-only fields are hidden on free keys. It also previews the returned fields (visits, MoM, organic share, DR, registration date, confidence).

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-loads the core search scope and return fields before the auth/logistics tail, with no filler sentences. The trailing auth URL and rate-limit clause make it slightly heavier than strictly necessary, but every element is useful.

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 7-param, no-output-schema tool it covers the essentials: what is searched, what comes back, auth and quotas. Sorting/ordering of results and pagination beyond the limit cap are not addressed, which is a minor gap given the annotations cover the safety profile.

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 defines every filter bucket and enum. The description's restatement of the filter set and the keyword targets adds little beyond the schema, and no bucket boundary values are clarified beyond the schema's enums.

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 (Search) plus a precisely scoped resource ('the current monthly board of new AI tool sites') and enumerates the query dimensions (domain/name/description) and filter axes. An agent can distinguish it from get_site (single site) and top_rising (ranking) without opening a 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 context for when this is the right tool (searching the current monthly board by keyword/filters) and routes the agent to list_categories for valid slugs. It stops short of naming when to prefer top_rising or revenue_signals instead, so no explicit exclusions are 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?

Annotations already declare read-only, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds meaningful context beyond that: it requires an API key with two possible headers, documents a free-tier quota (20 calls/day), and warns that Pro-only fields are hidden on free keys.

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 behavior is front-loaded in the first sentence, and the second sentence efficiently covers authentication, quota, and tier limitations.

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 list tool with no output schema and annotations covering safety, the description covers purpose, scope, ordering, authentication, quota, and tier limitations. It does not describe the return shape (e.g., which growth fields are present), but that is a minor omission for this complexity level.

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 both parameters are fully documented in the schema. The description reinforces that 'limit' controls the top N and that 'category' scopes the board, but it adds no syntax or format detail beyond what the schema already provides, 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?

The description states a specific resource ('this month's rising-sites board'), the ordering ('absolute monthly-visit growth'), and the optional scoping ('within one category'). This is clear enough for an agent to distinguish it from volume/record tools like get_site or search_sites, though no sibling is explicitly named.

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 what the tool returns and that a category is optional, but it gives no explicit when-to-use or when-not-to-use guidance relative to alternatives such as search_sites or list_categories. The only routing hint is the schema's 'see list_categories', which is in structured data rather than the description.

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