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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description contributes the non-obvious constraint that results are pinned to the most recent run, but with no output schema in place it does not explain the shape or granularity of what comes back.

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?

A single dense sentence with no filler, and the field list comes first so the reader learns contents before provenance. It is a fragment rather than a complete sentence, which slightly weakens readability but costs no space.

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?

For a zero-required-parameter read tool whose annotations carry the safety profile and whose single parameter is fully described, the definition covers what is returned and which run it comes from. The remaining gap is return structure, which normally an output schema would supply.

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?

Only one optional parameter, and the schema documents it completely ('One of ChatGPT, Perplexity, Gemini, Claude or Grok. Leave empty for all.'). The description's 'per engine' reinforces that the engine dimension drives the grouping, but adds no new syntax or default info beyond the schema.

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?

Names the concrete data returned (sentiment, summary, strengths, suggested improvements) and scopes it per engine from the latest AI visibility run, so an agent knows exactly what resource this is. It stops short of explicitly contrasting with siblings like get_ai_visibility or get_ai_competitors, which are the closest alternatives.

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?

Usage is only implied: the phrase 'from the latest AI visibility run' signals this is a read of existing perception data rather than a fresh audit, hinting that run_ai_visibility_audit is the trigger tool. No explicit when-to-use statement or exclusion versus get_ai_visibility is given.

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