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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description still contributes real value by explicitly stating that nothing is persisted to tracking, ruling out side effects an agent might otherwise assume from a 'suggest' verb.

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 short sentences, zero filler, with the core behavior stated first and the side-effect caveat second. Nothing could be removed without losing information.

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 described, and the description covers the essential read-only, non-persisting nature of the call. It leaves a small gap around how results relate to tracked competitors, but the critical invocation facts are present.

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 only 50%: storeProvider is well documented with its default behavior, but projectId has no schema description. The description mentions 'for a project and selected store' but adds no format, constraints, or default-resolution detail beyond what the schema already states, so it doesn't compensate for the gap.

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 ('Returns candidate competitor apps') and a scoped resource ('for a project and selected store'), which is clear enough to distinguish this from write-oriented siblings like add_keyword_competitors. It does not explicitly name the closest siblings (list_keyword_competitors, suggest_keywords), so it stops short of full differentiation.

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 clause 'Does not add competitors to tracking' implies that adding is a separate step and steers the agent toward a different tool for that, which is useful implicit guidance. However, it never states when to prefer this over list_keyword_competitors (existing tracked competitors) or suggest_keywords, nor does it name the tool to call next.

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