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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds genuinely useful context beyond them: checks run daily through a self-hosted backend that only approximates Google's ordering, so positions should not be treated as exact. It also explains the null sentinel and that deltas are signed with positive meaning upward, which pre-empts common misinterpretation.

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 main verb and resource are front-loaded, and the field-by-field clause reads as a compact enumeration of the returned row. The phrase "the most recent checks oldest first" is slightly tangled and the backend caveat could be tightened, but no sentence is 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?

For a no-parameter, read-only listing with an output schema, this is close to complete: safety, data provenance, sentinel values, delta sign convention, and ordering are all addressed. The remaining gap is practical scale — nothing says how large the result can get or whether truncation is possible, and the ordering clause is ambiguous about how many checks are included.

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?

This tool takes zero parameters, so the schema carries no semantics for the description to supplement and the baseline of 4 applies. The description correctly implies an unfiltered result set rather than inventing parameter-like knobs, though it could have warned that the listing returns every tracked keyword without filtering or paging.

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 opens with a specific verb and resource ("List the organization's tracked keywords with the latest rank check") and enumerates exactly what a row contains: position, matching URL, delta, and check history. The word "tracked" plus the rank-check detail implicitly separates it from sibling tools like webanto_list_keywords and webanto_list_keyword_actions, but no sibling is named, so the differentiation is inferential rather than explicit.

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 closing line, "Keywords are added, removed and checked from the dashboard; this tool only reads," does tell the agent this is a read-only surface and that mutations live elsewhere. However, it never names the obvious alternatives (webanto_list_keywords, webanto_list_keyword_actions) or states when to prefer them, so routing between the three keyword-related list tools is left to inference.

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