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

Annotations only declare the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds real behavioral context beyond them — per-keyword credit cost, depth-proportional cost because the provider bills per result, the auto daily re-measurement loop, and the crucial `position: null` with `measured: true` semantics. No contradictions with the annotations, and the null-vs-missing distinction is exactly the kind of thing structured fields can't convey.

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 and front-loaded, leading with what it does and the change-tracking payoff, then return fields, then the null-semantics caveat, then cost. Long but nearly every sentence adds operational value; the cost/top-up sentence is slightly promotional but still actionable.

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?

Given a 7-parameter mutation-ish tool with an output schema present, the description covers the risky/ambiguous behavior (costs, auto mode, null semantics) and routes history reads elsewhere. Return-value explanation is redundant with the output schema but harmless; only language/location semantics are unaddressed.

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 0%, so the description carries the full burden. It usefully explains the non-obvious parameters — `depth` (20 default, up to 100, cost implications), `device` (desktop/mobile rank differently), and `auto` (keeps re-measuring daily) — but says nothing about `language` (default 'tr'), `location` (default ''), `target`, or `keywords`. Roughly half the parameters are left to inference.

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 ('measures a domain's LIVE Google position for each keyword, stores every measurement, and reports the change') and distinguishes itself from the sibling it names, seo_rank_history. An agent can tell this apart from seo_ranked_keywords and seo_geo_tracker without opening either schema.

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 an explicit alternative for a specific need: 'Reading the stored history back is FREE: use seo_rank_history instead of re-measuring.' It also implies the repeated-run use case for change tracking. However, it doesn't cover when to prefer other ranking-adjacent siblings (seo_geo_tracker, seo_ranked_keywords) or prerequisites for enabling the add-on.

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