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

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered. The description adds real behavioral context the annotations lack: the returned field set and the 500-per-call ceiling. It does not discuss paging behavior beyond what the schema says, keeping it short of a 5.

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 sentences, front-loaded with the usage trigger, followed by return contents and then the exclusion. Every clause earns its place with no restatement of the tool name or title.

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 read-only list tool with a full output schema and annotated safety profile, the description supplies the routing context, return fields, and cap. Nothing needed to invoke 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% and each parameter (skip, limit, appId) is documented in-schema with bounds. The description only reinforces the cap ('up to 500 per call'), which is already implied by the limit maximum, so the 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 (list) and resource (tracked keywords) scoped to an app, and explicitly excludes adjacent capabilities: 'Not for current rankings or search volume.' An agent can separate it from get_keyword_rank and get_keyword_overview without opening a 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 trigger ('when someone asks which keywords they track for an app') plus a workflow trigger ('before adding or deleting one') that routes to add_keyword/delete_keyword, and names what it is not for. Nothing 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.