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

With no annotations, the description carries the full burden and does so well: facts come from a gated crawl respecting robots.txt and ToS, domains are normalized to the bare registrable domain (paths/queries/affiliates/subdomains stripped), new stores land as trust_tier=unverified, and look-alike/spam submissions are flagged with a reason rather than hidden. Rate limits and the dry-run escape hatch are also disclosed.

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?

Dense but front-loaded: purpose first, then data provenance, normalization, return shape, tier semantics, limits, dry-run, and the event alternative. Nearly every sentence carries information, though the paragraph is packed enough that scanning is harder than it needs to be.

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?

No output schema exists, yet the description supplies the full return shape ({id, domain, status: queued|duplicate|rejected, reason, trust_tier}), including the enum-like status values and the unverified default. For a 7-parameter, nested-object, zero-annotation tool, nothing an agent needs to call it correctly 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 coverage is already 86%, so the baseline is 3; the description adds real meaning beyond it by framing the inputs as 'only the domain, a category hint and an optional note' and explaining that agent_name is stored only as a salted id. The event alternative's required tags (["r", domain], ["t", category], optional ["proof", url]) are spelled out, which the nested-object schema does not do.

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: 'Suggest a store KlickyMart has not indexed yet,' which makes clear this is a write-side submission of new merchants. The 'not indexed yet' qualifier implicitly separates it from search_merchants/check_domain, but no sibling is named explicitly.

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 concrete operational context: dry_run=true validates without storing, and an alternative path exists via a signed kind 1423 event. It also states hard limits (10/day, 50/week per submitter and per salted network hash). It does not explicitly say when to prefer this over check_domain or recheck_domain.

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