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

Beyond the readOnlyHint annotation, the description discloses the setting's behavioral effects: it restricts storage to prospects, prevents non-prospect messages from triggering agents, and deletes previously stored non-prospect data when enabled. It also explains the downstream implication for search results, which is critical context an agent would otherwise lack.

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 front-loaded with the setting identity and then layers on effects and usage guidance in a logical order. It is somewhat verbose, but every sentence contributes useful context and there is little waste.

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 a simple read-only tool with one parameter and no output schema, the description is complete: it explains the setting's meaning, implications, and how to interpret empty search results, and it even describes the return value shape. An agent has everything needed to call and interpret it correctly.

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% and the single parameter on_behalf_of is fully documented in the schema. The description adds no additional parameter-level semantics, so the baseline of 3 is appropriate.

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 names the exact privacy setting, its location, and states that no tool changes it, clearly identifying this as a read-only getter. It is immediately distinguishable from siblings by focusing on the 'Only keep data on prospects' setting.

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?

It explicitly explains when to consult this setting (when a search for stored messages/emails/connections finds nothing for a non-prospect) and names the alternative tool fetch_linkedin_messages_with_person for reading LinkedIn conversations directly. This gives clear when-to-use and when-to-use-alternative guidance.

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