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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds the data-scope trait that this operates on the account owner's personal network rather than a company page. It does not address pagination via the cursor parameter, rate limits, or result limits.

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?

Three sentences, purpose front-loaded in the first sentence, use cases in the second, scope clarification in the third. Every sentence earns its place with zero filler.

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 read-only list tool with strong annotations and well-documented account_id, the description covers purpose, use cases, and scope. However, there is no output schema, so return format is unexplained, and the cursor (pagination) behavior is nowhere documented. An agent calling with search or paginating results gets no guidance.

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 only 33% — cursor and search are bare strings with no descriptions in the schema. The description partially compensates by implying search semantics through 'List/search' and examples like 'find Sarah in my network', but cursor/pagination behavior is never explained. account_id is already well documented in the schema, so the description adds little there.

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 verb+resource: 'List/search the LinkedIn connections of the account owner.' The use-case list ('who do I know at this company?', 'find Sarah in my network') and the closing 'This reads the user's personal network rather than a company page' clarify scope. It doesn't explicitly distinguish from near-siblings like linkedin_list_user_relations or linkedin_list_followers, though 'connections' is a precise LinkedIn relationship type.

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 gives explicit when-to-use examples ('Use for questions such as...', introductions, relationship mapping, connection-aware prospecting). It offers only an implied exclusion ('rather than a company page') and does not name alternative tools such as linkedin_search_people or linkedin_list_followers. This is clear context but lacks explicit when-not and named alternatives.

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