AIdata site search

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

Annotations already declare readOnly, idempotent, and non-open-world behavior, so the safety profile is covered. The description adds useful context beyond that: the output is Markdown and the tool operates on exactly one page. It does not itself mention the truncation ceiling, though max_chars is documented in the schema.

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 short sentences, front-loaded with the action and output format, then accepted inputs, then routing guidance. No filler; every sentence carries distinct 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 two-parameter read tool with full schema coverage, an output schema, and rich annotations, everything an agent needs is present: purpose, input forms, discovery alternatives, and return format. No significant gap remains.

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, but the description adds concrete accepted forms ('/pricing/', '/docs/getting-started/', absolute URL) that make the url parameter unambiguous beyond the schema's generic wording. The max_chars default/limit 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?

States a specific verb and resource (fetch one page) plus the return format (Markdown) and the accepted input shape. It clearly differentiates from the sibling tools by positioning get_page as the reader and list_pages/search_site as discovery tools.

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 routes the agent: 'Use list_pages or search_site to find URLs,' naming the alternatives and the condition that selects them. Combined with the accepted path/URL forms, an agent knows both when to call this tool and how to obtain its input.

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 and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the response is structured data, it spans three currencies, and the BYOK note clarifies that AI usage billing is explicitly out of scope, preventing an agent from assuming this tool reports usage costs.

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 return payload before the BYOK caveat. The content list is dense but each clause maps to a distinct field set the caller would otherwise have to discover.

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 zero parameters, rich annotations and an output schema present, the description only needs to frame intent and scope, which it does. Nothing critical is missing, though a one-line pointer to a sibling (e.g. sign-up flows) would make it airtight.

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 and there is no schema semantics for the description to supplement or contradict. No further parameter explanation is needed.

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 (retrieve current AI Data Stream plans) and enumerates exactly what the payload contains: monthly/annual prices in USD, GBP and EUR, tier inclusions, trial terms, extra seat cost and sign-up links. Against generic siblings like get_page and search_site, an agent can immediately tell this is the authoritative pricing source.

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 resource name and the enumerated contents, but there is no explicit when-to-use statement and no routing against alternatives (e.g. 'use this rather than scraping pricing via get_page'). Adequate but leaves 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 declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safe, repeatable read profile is covered. The description adds that filters are optional and what fields come back, but says nothing about result size, pagination, or ordering — modest added value over the 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 tight sentences with the core purpose and filter scope front-loaded and the discovery-use hint appended. No filler or redundancy.

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-value details need not be spelled out, and the description still notes title/description are included. For a 2-parameter, read-only, zero-required listing tool this is nearly complete; only pagination/result-size behavior 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 50%: lang has only "Default en." while section is undocumented in the schema. The description re-lists the section enum values (docs, blog, changelog, core) that the schema already provides and mentions language filtering, but adds no new syntax, defaults, or behavior beyond the structured fields.

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 (List) and resource (pages), names the source (aidata.stream), and specifies the returned fields (title and description). This makes it clearly distinct from get_page (single page) and search_site (query-based) 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?

"Good first call to see what documentation exists" gives clear context for when to reach for this tool as a discovery entry point. It does not, however, explicitly exclude or name alternatives like search_site for targeted lookups, so it stops short of full when-not 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, not open-world), so the bar is lower; the description still adds useful behavior, namely the return shape (best-matching sections with snippet plus URL and anchor) and the language-scoping model. It stops short of explaining result ranking or how limit truncation behaves.

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, zero filler: scope and return value first, follow-up tool second, language caveat last. Every sentence carries information an agent needs.

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 needn't detail return values, and it covers scope, language, and the handoff to get_page. The one remaining gap is disambiguation against get_pricing/list_pages, which matters more here than return detail.

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 query, lang, limit and section are all documented in the schema itself. The description only restates the language default ('English by default; pass lang for the French or German site') without adding format or syntax guidance beyond it, 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?

States a specific verb and resource ('Full-text search across aidata.stream') and enumerates the exact corpus covered: docs, blog, changelog, pricing, FAQ, home. It also distinguishes itself from the sibling get_page by positioning search as the discovery step and page-reading as the follow-up.

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 tells the agent what to do next ('Use get_page to read a whole page afterwards') and clarifies the language default with an escape hatch. It does not say when to prefer get_pricing or list_pages over a search, so routing among all four siblings is only partially covered.

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