forage

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

With no annotations provided, the description carries the transparency burden. It does disclose useful behavioral details: fetches public URLs, returns main content in markdown, has a free daily quota, and then becomes pay-per-call. However, it does not explain what 'main content' means, how much boilerplate is stripped, or what happens on failures, redirects, or non-public URLs.

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, zero filler. The core action and output format are front-loaded, and the pricing constraint is added in a compact final clause. Every word earns its place.

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?

The tool is simple: one required URL parameter, one optional length cap, and no output schema. The description covers return format and quota behavior. It could mention error cases or non-public URL handling, but for a basic fetch-to-markdown utility with fully documented parameters, it is reasonably 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%, so the schema fully documents both url and maxChars. The description adds no parameter-specific semantics beyond what the schema states, leaving the baseline of 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 clearly states the verb ('Fetch'), the resource ('any public URL'), and the output ('main content as LLM-ready markdown'). It naturally distinguishes itself from the sibling web_search tool: scrape targets a specific known URL while web_search finds URLs via a query.

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 rather than explicit: if you have a direct URL and want its content, use scrape; if you need to find a URL, use web_search. The description does not explicitly state when not to use the tool or name alternatives, but the semantics are clear enough for basic 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?

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose the free-tier quota and pay-per-call pricing model, which is genuinely useful cost context. However, it doesn't describe what the JSON response contains beyond the listed result types, error behavior, or rate-limit specifics. The disclosed quota info is solid but the description is thin on other behavioral traits (e.g., pagination semantics, degradation under heavy use).

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 filler. The core search behavior is stated first, and the pricing constraint is appended as a second sentence. Brief and informative, though the pricing detail might be more useful after scope and usage context; structurally it is still clean and front-loaded on the primary 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 search tool with 100% schema coverage and no output schema, the description covers the behavior, the result types, and the cost model. The return value shape is only partially specified (mentions JSON and the result types) but no output schema is provided, so the description is doing reasonable work there. Missing error-handling and explicit alternative routing, but adequate for typical search invocations.

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% for the five parameters, so the schema and description together fully document 'q', 'gl', 'hl', 'num', and 'page'. The description adds the pricing/quota context that the schema does not carry, which is a real increment. But it doesn't add semantic nuance beyond what the schema already states — no formatting, defaults, or interplay hints. Baseline 3 is correct given full schema coverage.

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 ('Google web search') with a clear resource, and enumerates the result types delivered (organic results, answer box, knowledge graph). This distinguishes it well from its sibling tool 'scrape' — one searches, the other scrapes a page. The scope 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?

It identifies the search domain and output format, which implies when to reach for it, but it does not explicitly state when to avoid it or when to use the sibling 'scrape' instead. The distinction between search and scrape is reasonably inferable, but the description does not proactively route the agent.

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