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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds genuinely useful behavior beyond them: a hard batch cap of 20, an immediate ranking fetch triggered per keyword, partial-failure semantics ('per-keyword error in `results`'), and silent reactivation of removed keywords. It stops short of mentioning credit/quota cost or rate limits for the immediate fetch.

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?

Three tight sentences, front-loaded with the capability and batching limit, then side effects, then the app_id provenance hint. No filler or redundancy.

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 5-required-parameter write tool with no output schema, the description supplies the essentials: batch cap, immediate-fetch side effect, per-keyword error reporting in `results`, and reactivation behavior. It references the `results` field but does not describe the overall response shape, a minor gap given no output schema exists.

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 100%, so all five parameters (including the lang/store/country nuances) are already documented in the schema; the baseline is 3. The description's only added hint, 'Use app_id from list_applications results', restates what the app_id schema description already says, and the 20-keyword limit is likewise already in the array constraints.

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 gives a specific verb (Track), resource (keywords), scope (up to 20 new keywords for one application in a single call), making it immediately distinguishable from siblings like untrack_keyword, list_keywords, and inspect_keyword. An agent can tell what the tool does without opening the 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?

It states the context for invocation ('Use app_id from list_applications results') and handles edge cases — already-tracked keywords return a per-keyword error, previously removed keywords are reactivated. It does not explicitly name untrack_keyword as the inverse or spell out when-not-to-use, but the intended usage is unambiguous.

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