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

Beyond annotations, the description discloses meaningful behavioral details: first enable creates an agent and template workflow, later calls resume or pause, one watcher per kind per account across workspaces, and specific error conditions (DUPLICATE_*_EXTERNAL, AGENT_ACCOUNT_UNAVAILABLE). This is far richer than the raw annotations alone and matches the idempotentHint.

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 dense but efficiently organized: main action first, then lifecycle, cross-workspace constraint, auth prerequisite, and a pointer to the read tool. Every sentence adds operational value and none is redundant.

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?

The description covers creation, resumption, pausing, workspace ownership limits, session requirements, error cases, and how to read current state. For a state-toggle tool with no output schema, this is unusually complete; an agent has enough context to call it correctly and interpret common failures.

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?

With 0% schema description coverage, the description compensates well: it explains kind values (connection watcher vs message watcher), enabled behavior (on/off, first enable creates), and the LinkedIn account scope. It also gives workspace-related context, though it never explicitly names workspaceId or states how it should be supplied, so a small gap remains.

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 opens with a precise verb and resource: turning a LinkedIn account's connection watcher or message watcher on or off. It also distinguishes the tool from the read-only sibling by explicitly directing to campaignstack_get_account_maintenance for reading state, and clarifies that first enable creates the agent while later calls resume/pause.

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 guidance: enabling requires a live LinkedIn session, and a watcher owned by another workspace cannot be controlled from here. It also names the alternative for reading state (campaignstack_get_account_maintenance) and explains the lifecycle difference between first enable and later resume/pause calls.

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