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

Annotations only declare it is a mutating, idempotent, non-destructive, open-world write; the description adds genuine behavioral context beyond that — the risk profile of raising daily caps (elevated LinkedIn restriction risk) and the blast radius of isPaused (it stops every campaign on the account, not one). It also scopes out operations it cannot perform (connect/disconnect, session repair, campaign attribution), so the agent will not misuse it.

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, each with a distinct job: settings scope, risk/routing for `limits`, then blast radius plus exclusions. The highest-risk item (raising limits) is placed ahead of the lower-stakes disambiguation, so the agent reads the caution before acting.

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?

Ten parameters including a nested object, no output schema, and only coarse annotations — yet the description closes every meaningful gap: what the fields do in aggregate, the risk of the one dangerous field, the side effect of pausing, and the adjacent tools that handle the things this one does not.

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%, so the nested `limits` sub-fields and boolean toggles are already documented; a 3 is the baseline. The description nonetheless adds decision-relevant meaning the schema cannot carry — that `limits` is a high-risk field to be left untouched absent an explicit user request — which is the single most important semantic for this tool's parameters.

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?

Opens with a specific verb + resource ('Change the safety limits and automation settings on a LinkedIn account') and enumerates the exact setting groups: daily caps, pause/resume, warm-up, and the three auto-congratulation messages. An agent can immediately distinguish this from linkedin_account_get, linkedin_account_refresh, and campaign_set_status.

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?

Explicit when-not guidance with named alternatives: 'to stop one campaign use campaign_set_status with PAUSED, and to stop one lead use lead_update.' It also states a prerequisite check ('check linkedin_account_daily_stats first') and a caution on when not to touch `limits` unless the user asked for a specific number.

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