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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value by disclosing the exclusion behavior (already-tracked terms are filtered out) and that suggestions are not persisted. It does not mention that idempotentHint=false means repeated calls may yield different AI-generated results, which would have been a useful addition.

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?

Two tight sentences with zero waste; the core behavior is front-loaded and the non-persistence caveat follows immediately.

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?

An output schema exists, so return values need not be explained, and the read-only nature is covered by annotations. The description is nearly complete, with only the non-determinism of AI suggestions left unstated.

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 50%: storeProvider is documented in the schema, but projectId is not. The description's references to 'project metadata' and 'the selected store' loosely map to both parameters, but it adds no format or defaulting detail beyond what the schema already provides.

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 ('Returns AI-assisted keyword ideas') plus the scope ('based on project metadata, excluding terms already tracked'). This clearly distinguishes it from add_keywords and list_keywords, which track or enumerate rather than suggest.

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?

'Does not start tracking suggestions' implicitly routes the agent to add_keywords for persistence, giving clear usage context. However, it never names the alternative tool explicitly, so the agent must infer the pairing.

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