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

Annotations declare readOnlyHint=true and destructiveHint=false, but the description goes far beyond by disclosing proxy-aware fetching, the fallback path (/pricing, /plans, homepage), extraction fields, cache TTL, and the critical failure behavior: 'returns a clear degraded result with warnings and signals — never fake success.' This is rich behavioral context that structured annotations do not provide.

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 information-dense but appropriately sized at two sentences. It front-loads the core purpose, then packs in fetch strategy, extraction list, failure handling, ICP, proxy variable, and cache TTL. No fluff or repetition. While it could be restructured into bullet-like clarity, it remains efficient and focused.

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 scraping tool with network dependencies and failure modes, the description covers all essential context: input URL/domain, fetch paths, extraction fields, degraded-result behavior (no fake success), proxy awareness, and caching. The presence of an output schema reduces the need to describe return values, and the failure semantics plus caching TTL make this complete for an AI agent to invoke confidently.

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% (both url and async are described in the input schema). The description adds no new parameter-level meaning beyond the schema, though it reinforces the 'direct pricing page URL' suggestion in the schema. Baseline 3 is appropriate as the schema does the heavy lifting and the description does not compensate further.

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 uses a specific verb-resource pair: 'Scrape and parse a competitor pricing page from a URL or domain.' It clearly distinguishes this from sibling tools like competitor_pricing_radar (which likely tracks pricing over time) and pricing_strategist (which recommends pricing) by focusing on direct scraping from a given URL/domain. The extraction details (plan names, prices, billing cadence) make the purpose unmistakable.

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 clear context: it is for scraping a specific competitor URL/domain, and it names ICPs (founders, PMs, pricing strategists). It also implies when not to use it (when no specific URL is available) but does not explicitly reference alternative tools or exclusion criteria. The 'For best results, provide the direct pricing page URL' guidance in the schema adds usage nuance.

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