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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful behavioral context: the operation is read-only and free, and it discloses the sampling caveat that changes should be treated as indicative unless the sample count licenses otherwise. This goes beyond the structured annotations.

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 dense but front-loaded with the core purpose, then adds sampling caveats and drill-down guidance. A few phrases are packed together, but each sentence earns its place and the structure supports a complex read-only reporting tool.

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 carries the burden of explaining what results include, and it does: engine answers, share of voice, cited sources, gaps, trend, crawlability, off-site reach, sample counts, and the drill-down parameter. It also embeds the critical sampling interpretation and workflow placement, making it complete for correct invocation.

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% and the single optional parameter is already described in the schema as drilling into one tracked question for engine answer text and citations. The description repeats this without adding material new semantic detail, so the baseline 3 applies.

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?

Description clearly names the resource: measured AI visibility (GEO) results across specific engines, plus components like share of voice, cited sources, and trends. It is unambiguous about what get_visibility returns, though it does not explicitly contrast itself with sibling tools like get_seo by name.

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 explicit sequencing: 'Read after refresh_scan and before any AI visibility or GEO work.' It also explains when to pass prompt_id for drilling into a single question. It does not name alternatives or state when-not-to-use, so it stops short of a 5.

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