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

Goes well beyond the readOnlyHint/destructiveHint annotations by disclosing billing ('Costs 1 credit'), an auth prerequisite ('Needs a free StartupHub.ai account'), and caching semantics (stored fingerprint vs. live read). Missing only failure modes or rate-limit detail.

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?

Five short sentences, front-loaded with the identity line, then output, then the caching rule, then cost and account requirement. Every sentence carries distinct information with no padding.

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 read-only scan with no output schema, the description adequately covers the returned categories, cost, and auth requirement. It leaves the exact response shape unspecified, but nothing needed to invoke the tool correctly is absent.

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 both parameters are already documented in the schema. The description adds mild reinforcement ('Accepts a URL or a plain domain') but no syntax or format detail beyond what the schema already provides, matching the 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?

States a specific verb and resource ('Return hosting, frameworks, analytics, payments, and mail setup for a company website') with the returned categories enumerated. No sibling tool covers tech-stack detection, so it is unambiguously distinguishable from scan_agent_readiness or check_site_speed.

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?

Explains the caching decision rule precisely: a stored fingerprint is checked first, and a fresh live read happens when live=true. It does not name alternatives or exclusions, but no sibling overlaps, so context is sufficient without them.

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