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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does a solid job: it reveals that responses preserve bounded-context limits, include truncation warnings, retain evidence, and reference page-on-demand stored-content. These are genuinely useful behavioral traits an agent needs to anticipate before calling, going beyond a mere 'extracts pages' statement.

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 tight at two sentences, front-loading the core purpose before the behavioral notes. No filler or redundant phrasing, though the second sentence is dense with jargon (bounded-context limits, page-on-demand stored-content) that could be simplified.

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 tool with 8 parameters, no annotations, and no output schema, the description is too thin. It explains provider-source behavior but omits guidance on key options like rendering JavaScript, image/raw-HTML inclusion, or the semantic-span selection feature. An agent cannot infer how renders_js or include_raw_html affect output from this text.

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 only 38% across 8 parameters, and eight parameters (spans, format, render_js, include_images, include_raw_html, spans_query, provider) receive no explanation in the description. The only link is the mention of '9 providers', which loosely maps to the provider enum, but the description does not compensate for the heavy schema gap.

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 verb+resource pair ('source-only URL extraction' from URLs) and names the 9 providers behind it. 'Source-only' clearly implies the tool works from given URLs rather than search terms, which helps distinguish it from its only sibling web_search, though it never names that sibling 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?

'Source-only URL extraction' implies the tool is for extracting content from URLs you already have, and by contrast web_search would be for discovering URLs via queries. However, the description never explicitly states 'use this when you have URLs' or 'use web_search when you need to find pages', leaving the routing decision 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?

With no annotations, the description carries the full burden of behavioral disclosure. It does reveal non-obvious behavior such as routing across providers, returning cache provenance, and emitting typed errors. However, it does not explain how results are structured, how caching affects behavior, or what side effects or limitations exist.

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 sentence and front-loaded with 'web search', but it is dense with undefined jargon such as 'additive v3 evidence' and 'routing receipts'. It is concise in length but not in clarity, and the value of several phrases is questionable.

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 16-parameter tool with no annotations and no output schema, the description is far too thin. It does not explain the shape of returned evidence, the meaning of 'source-only', how provider routing works in practice, or when to set key options like mode, depth, or provider. An agent would need to rely entirely on the 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 the baseline is 3 even though the description itself adds no parameter-level meaning. The description's mentions of routing and cache provenance thematically relate to parameters like provider and no_cache, but it does not enrich the parameter semantics beyond 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 verb and resource ('web search') and differentiates it from the sibling web_extract by emphasizing search rather than extraction. However, 'source-only' and 'Web Search Plus v3 runtime' are jargon that obscure rather than clarify the core function.

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 guidance on when to use this tool versus web_extract or any alternative. The description implies a search use case but does not state when it is appropriate, when it is not, or what conditions would route an agent to a sibling tool.

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