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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint, so behavioral safety is covered. The description adds transparency by stating it 'probes each entity with ai_visibility_check' and returns a ranked list with score, confidence, signal density. This informs the agent of the sub-tool dependency and output format without contradicting 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 two sentences long, front-loads the core action, and contains no filler. Every phrase earns its place, achieving high density of useful 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?

Given the tool has 4 parameters (1 required), no output schema, and no nested objects, the description is complete. It describes input (entities, models, etc.), process (probes each, ranks), and output (ranked list with score, confidence, signal density). The annotations cover safety, and no further detail is needed.

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%, with clear descriptions for all 4 parameters. The description adds one piece of semantic value: the first entity in the array is treated as the 'subject' for narrative purposes, which is not in the schema. This enhances the agent's understanding of parameter usage.

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 clearly states the tool compares AI visibility across multiple entities side-by-side, using specific verbs like 'compare', 'probes', 'ranks', and 'surfaces'. It distinguishes from sibling tool 'ai_visibility_check' which likely operates on a single entity, and 'compare_entities' which is more generic. The example query solidifies the purpose.

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 description provides explicit use context: 'competitive AI-marketing audits' and an example. It implies when to use (multi-entity comparison vs. single check) but does not explicitly state when not to use or name alternatives beyond sibling tools. The note about first entity as 'subject' for narrative adds clarity.

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