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

The description discloses meaningful behavior beyond the annotations: first-run snapshot, weekly re-read/diff, emitted company_employee_joined signal, idempotency, and per-workspace caps. It does not detail permission requirements or failure modes, but the annotations already cover safety traits like readOnly and destructive hints.

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?

Two dense sentences carry all key information: purpose, mechanics, cadence, side effect, idempotency, cap, and sibling distinction. Nothing is wasted and the core action is front-loaded.

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 two-parameter creation tool with no output schema, the description covers the essential operational details: what the watch does, when it runs, what it emits, and its limits. It could mention how to list, pause, or remove the watch, but those are covered by sibling tools and do not block correct invocation.

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 must compensate. It references 'company' and 'workspace' enough to imply what companyId and workspaceId mean, but it does not explicitly define the format, source, or validation of these IDs. The parameter names are self-explanatory, but the description could be more direct.

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 states a specific verb and resource: 'Watch a company for NEW employees' and explains the signal it emits. It also explicitly distinguishes itself from campaignstack_create_signal_watch, so an agent can tell these sibling tools apart.

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?

It clearly explains the intended use case (tracking new employees at a company) and names the closest alternative, campaignstack_create_signal_watch, with the deciding condition: company-level vs person-level watching. The lifecycle (first snapshot then weekly diffs) also clarifies when ongoing behavior kicks in.

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