Track keywords

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false), and the description adds genuine behavioral context beyond them: each keyword triggers an immediate ranking fetch (a cost/side effect), duplicates produce per-keyword errors in `results` rather than failing the call, and removed keywords are reactivated automatically. These side-effect and partial-failure semantics are exactly what an agent needs before calling a non-idempotent mutation.

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?

Four tight sentences, each carrying distinct information: operation scope, side effect, duplicate/error handling, reactivation, and the required ID source. The most decision-relevant fact (immediate ranking fetch) and the cap are front-loaded with no wasted prose.

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?

With no output schema, the description still explains the return surface by naming the `results` field and its per-keyword error content, and it covers the mutation's side effects and edge cases. For a 5-required-param mutation tool, nothing essential to correct invocation 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 description coverage is 100%, so all five parameters are documented in the schema itself. The description adds only the 20-keyword cap (already in the schema's maxItems) and repeats the app_id provenance note, so it does not meaningfully extend parameter meaning. Baseline 3 applies.

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 ('Track up to 20 new keywords for one of your applications') with an explicit scope cap, clearly distinguishing it from siblings like untrack_keyword and list_keywords. An agent can identify the operation 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?

Gives a clear usage condition (adding new keywords) and a concrete prerequisite ('Use app_id from list_applications results'), plus edge-case behavior for already-tracked and previously removed keywords. It stops short of explicitly naming untrack_keyword as the inverse alternative, so it is one step below full when/when-not guidance.

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