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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it discloses the return shape (success, creditsUsed, id, data.web[]), the limitation to titles/snippets, measured latency (~15s for 2 results, slowest of search tools), and billing behavior (ceil(limit/10)*2 credits). It also discloses rejection of unsupported modes. This is rich, non-redundant behavioral disclosure.

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 dense but well-organized: it front-loads the core purpose and return shape, then adds performance, billing, and routing guidance. Every sentence earns its place, though the length is substantial. The structure is logical and scannable, with the alternative routing at the end. Slightly long but not bloated.

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?

Given the tool's complexity (2 params, output schema present, annotations covering safety), the description is complete. It covers return format, performance, billing, platform constraints, and alternatives. The output schema already documents the response structure, so the description doesn't need to repeat it. Nothing an agent needs to decide whether to call this tool 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?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds meaning by explaining the billing implication of limit (ceil(limit/10)*2 credits) and the latency implication, which goes beyond the schema's 'Maximum number of results to return.' It also clarifies that query is required and that limit controls result count, but the schema already covers that. The added cost/latency context justifies a 4 rather than baseline 3.

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 opens with a specific verb and resource ('Search the web and get back ranked results') and immediately distinguishes itself from sibling search tools by naming alternatives and their conditions. It clearly states what the tool returns (titles and snippets only, no page text), which differentiates it from post_tavily_search, post_exa_search, and post_firecrawl_scrape.

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 provides explicit when-to-use and when-not-to-use guidance: it names post_tavily_search for page text in the same call, post_firecrawl_scrape for known URLs, and post_exa_search for meaning-based relevance. It also states platform constraints (AIsa metered profile supports only web source; scrapeOptions, enterprise mode, non-web sources rejected). This is exemplary routing guidance.

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