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

Beyond the readOnlyHint annotation, it discloses the behavioral edges an agent needs: results under 300 members are not delivered by LinkedIn (too_small), and targeting_notice is a mandatory notice that must be shown to the user verbatim with its link. It also restates the non-mutating nature, consistent with the 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?

Front-loaded with the purpose, then input modes, then return values and the mandatory-notice caveat — nothing wasteful. The single dense block and the enumeration of return fields (which the output schema already covers) cost it a point.

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 an open-world, four-param read tool with an output schema, the description covers what an agent needs to call it correctly: both input modes, the workspace scoping, the minimum-size caveat, and the user-facing notice obligation.

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 0%, so the description carries the load — and it does, explaining include/exclude (structure borrowed from linkedin_update_campaign_targeting, locations required), campaign_id as the alternative input, and workspace being optional for single-workspace setups. The internal shape of the include/exclude objects remains only indirectly specified.

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: estimated LinkedIn audience size for a targeting. It also disambiguates from the sibling that produces targeting data by naming linkedin_update_campaign_targeting as the source of the include/exclude shape, and it explicitly says it is a non-mutating estimate.

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 clear mode selection: either pass include/exclude directly (with locations required in the group) or pass campaign_id to estimate an existing campaign's targeting. It does not, however, say when to prefer this over siblings like linkedin_search_targeting or linkedin_audience_breakdown.

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