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

Adds substantial context beyond annotations: results are computed at call time from the last 30 whole UTC days of answers plus a live check of the client's website, and the agency view is capped at 10 brands. The 'Changes nothing' note is consistent with readOnlyHint and reinforces safety, though return formatting details remain sparse.

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 one very long, dense sentence with nested parentheticals, making it difficult to scan. The key scoping information is front-loaded, but the middle sections are harder to parse than necessary.

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 does a good job explaining return content: priority, rationale, affected prompt count, domain/engines, and howToRead. It is nearly complete for an agent to call the tool correctly, though the action object structure is only summarized.

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 description coverage is 100%, so the baseline is 3; the description earns an extra point by clarifying the interaction between projectId and clientId, including the fallback behavior when neither is supplied. It does not add much detail on source or priority beyond what the schema already states.

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 resource (prioritised actions on the AI Visibility Insights page) and enumerates the action categories, including the special Gap analysis action. It also names the sibling get_signals as the place to find detected changes, so an agent can separate the two without ambiguity.

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?

Explains that projectId or clientId selects one brand, and that omitting both returns the agency page across every brand with a scan (at most 10). It also routes change-detection needs to get_signals, but does not give a full when-not-to-use statement beyond that.

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