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

Goes well beyond annotations: discloses the 1-credit-per-keyword cost model, free-tier cap of 5 keywords/day per IP, API-key removal of the cap, and the `pending` state (queued, not charged) with retry_after_seconds re-check advice. Annotations only cover readOnly/idempotent safety; this adds the operational behavior that actually matters for invocation.

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?

Front-loads the primary purpose, then cost, then limits, then sibling alternative, then edge-case handling. Every sentence earns its place; no 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?

Complete for a read-only metric tool with no output schema: covers purpose, cost, auth/free-tier, sibling routing, and the async pending/retry edge case. 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 100%, so the baseline is 3, but the description adds value beyond it: it clarifies the bulk-vs-single distinction ('or up to 25 in bulk') and that they are mutually exclusive, and that the pending/retry behavior is a return-value trait tied to keyword computation. Slightly above baseline for reinforcing the key constraint.

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+resource ('Difficulty + popularity for a specific keyword') and explicitly contrasts with the sibling sonar_keyword_search ('use sonar_keyword_search instead when you want related keyword ideas'). An agent can distinguish it from siblings immediately.

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?

Explicit when-to-use ('when you already know which keywords you care about') and a named alternative with its selection condition ('sonar_keyword_search ... when you want related keyword ideas alongside metrics'). Credit-cost and free-tier limits add actionable routing context.

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