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

Annotations declare non-readOnly, non-destructive, open-world, non-idempotent; the description adds value beyond that by disclosing the merge policy ('only fills fields that are still empty'), so existing data is not overwritten, and by requiring a confirmation step with the user. It is silent on failure behavior (unreachable site, no extractable content) and on how the scrape's open-world fetch is bounded.

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, zero filler, and the core action plus its distinguishing constraint are front-loaded in the first sentence. Every remaining sentence adds either usage context or a required UX step.

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 no output schema, the description carries the burden of saying what comes back — it names the extracted fields (name, category, description) and that results must be shown to the user for confirmation. The main gap is that it says nothing about outcomes when scraping fails or finds nothing, which an agent handling a 1-param, network-dependent tool would benefit from.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents websiteUrl including the 'https://' format requirement. The description adds the semantic that it must be the user's own site but no format or validation detail beyond the schema, making the baseline 3 correct.

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 (scrape, auto-extract) and resource (the user's website → profile fields: business name, category, description). The parenthetical 'only fills fields that are still empty' gives an agent a precise differentiator from generic profile-writing siblings like update_business_info or set_brand_identity.

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 scopes usage ('Use during onboarding') and states the user-facing workflow ('Show the user what was found and confirm it'), which tells the agent when in the flow to call it and what follows. It does not name the near-alternatives (research_brand, update_business_info) or say when not to use it, so it falls short of a 5.

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