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

Goes well beyond the read-only/openWorld annotations: it discloses the return shape (score out of 100, points per check, concrete actions), the runtime (5–15 seconds), and the nuanced scoring rule that blocking training bots costs only 5 of 20 points while blocking user-fetch bots costs 15. That is substantial behavioral context an agent cannot infer from structured fields.

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?

Purpose is front-loaded and the dense paragraph is mostly information-bearing, with the scoring model and runtime carrying real value. A few clauses are long and could be tightened, but there is little pure filler.

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 explaining returns and does so (score, per-check points, concrete actions). Combined with runtime, the check set, and profile semantics, an agent has everything needed to call this correctly.

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%, so baseline is 3, but the description adds real meaning: it explains each yardstick's scope (government = public bodies, organisation = NGOs/associations, party = political parties, media = news media) and that detection happens unless profile is supplied. That exceeds the raw enum list.

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 (checks) and resource (how a public website looks to AI assistants), then enumerates the exact things examined (robots.txt, sitemap, schema.org, llms.txt, ai-catalog.json, prompt-injection text). This is clearly distinguishable from the find_* and check_business siblings.

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?

Gives clear context for the profile parameter ('Optional yardstick. Leave out to detect it from the site') and explains the scoring model, so the agent understands when a profile override matters. It does not explicitly contrast with the sibling check_business or state exclusions, so it stops short of 5.

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