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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), it enumerates the exact failure modes (active_prompt_limit_reached, setup_branded_limit_exceeded, prompt_not_found, saved_prompt_limit_reached, check_running) and the side effects it does not cause ("starts no check and reserves no observations"). It also describes the return payload and the skip reasons (already_active, paused, edit), which is unusually rich disclosure for a mutation tool.

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?

Front-loaded with the core action and the primary routing fact, and nearly every clause carries operational content. The refusal enumeration makes the single paragraph dense and slightly run-on, which costs it the top score, but there is no filler.

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 takes on the job of describing the result (all Active prompts of the market plus skipped custom prompts and reasons) and it does so explicitly. Combined with the named preconditions and error codes, an agent has enough to call it correctly and interpret outcomes.

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%, so per-property docs already exist; the description still adds meaning by explaining that selectedPromptIds must be 'a selectable Suggested prompt of the market' and that a customPrompts text matching an Archived prompt re-activates it. That's real semantic value beyond maxLength/topic constraints, though array-level ordering/dedup behavior is not addressed.

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 effect ("Makes prompts Active for a site") plus the two input channels it acts on, and ties the behavior to the AI Visibility page's confirmation action. It also names the sibling that owns the adjacent operation ("only update_visibility_prompt can change"), so the agent can separate this from update_visibility_prompt without inspecting schemas.

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 concrete precondition ("Pass at least one prompt"), points at get_visibility's suggestions section as the source of selectedPromptIds, and routes the edit case to update_visibility_prompt. It stops short of an explicit when-not-to-use statement or a clear 'use start_visibility_check instead' alternative, which keeps it below a 5.

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