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

Annotations already cover read-only/idempotent/no-destructive, but the description adds substantial context beyond them: the ~300-member delivery floor, the silent-failure consequence, the returned fields (audience_size, below_delivery_minimum), and the diagnostic meaning of a 0 result. That is exactly the behavioral detail structured fields cannot express.

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-loads the core purpose and the pre-flight role, then the two modes, then the diagnostics — a logical order with no filler sentences. It is dense but each paragraph earns its place; the shouting capitals for emphasis are slightly noisy but not wasteful.

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 forecast tool with 14 optional targeting parameters and an existing output schema, the description supplies everything needed to choose the right mode and interpret the response, including the edge cases (archived audience, mutually exclusive facets). Nothing material is missing.

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% across 14 parameters, so the description carries the load. It clarifies the crucial campaign_id-vs-URN-arguments fork and states that the URN arguments mirror those of update_linkedin_campaign_targeting, which is meaningful guidance. It does not explain individual facet parameters (geo_urns, seniority_urns, exclude_audience_urns, etc.), leaving their semantics to naming convention alone.

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 and resource ('asks LinkedIn HOW MANY MEMBERS a targeting setup reaches') and explicitly positions itself against siblings create_linkedin_campaign and update_linkedin_campaign_targeting. An agent can distinguish it from linkedin_targeting_search and get_campaign_targeting without opening a schema.

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 explicit when-to-use ('the pre-flight check to run BEFORE create_linkedin_campaign / update_linkedin_campaign_targeting') plus the failure mode that motivates it. It also delineates two modes of operation and tells the agent which argument set selects which mode, including the fallback pointer to list_linkedin_audiences when the result is 0.

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