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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description doesn't need to repeat safety. It adds valuable behavioral context: the list is recomputed on every read, the dismissed set is carried and disjoint, and that decisions rest with the user. This exceeds the shallow safety info in annotations, though it doesn't detail the exact return format or pagination.

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?

The description is thoughtfully structured: it opens with the core purpose, then explains the recomputation, the dismissed list, and the disjointness, and ends with user guidance. While longer than two sentences, each sentence carries distinct information and no fluff, and the most important fact is front-loaded.

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?

The description is comprehensive for a tool with no output schema. It explains what the response contains (suggestions and dismissed list), their relationship (disjoint), how the data is computed, and the appropriate action (relay to user). It also gives the restoration path, ensuring an agent can act correctly without additional context.

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?

With only one required parameter and 100% schema description coverage, the schema already documents tracker_id as the UUID and directs to list_trackers. The description adds no additional parameter semantics; it operates at baseline because the schema covers the parameter fully.

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 clearly states the tool lists keyword suggestions discovered on a tracker, specifying the resource (tracker) and the precise nature of the suggestions (domains engines cite repeatedly and that no tracked keyword covers). It distinguishes from sibling tools like restore_keyword_discovery and dismiss_keyword_discovery by explicitly defining the discovered set and its disjointness from dismissed domains.

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?

The description gives explicit usage guidance: present the suggestions to the user and leave the tracking decision to them. It also indicates when to use restoration (if the user changes their mind) and clarifies that dismissed domains are excluded, implicitly steering the agent to this tool for presenting viable suggestions rather than restore operations.

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