Notify a CRM agent

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds two genuinely new facts beyond that: content is plain text only, and no customer is contacted. It still leaves open whether the notification is transient or persisted, and what happens if the target agent is unavailable or the identifier is invalid.

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 short sentences, front-loaded with the core action, then the format constraint, then the scope exclusion. Nothing is redundant and no sentence is filler.

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 low-complexity mutation with annotations and full schema coverage, the essentials are present. Still missing: how to choose between agent_id and agent_name, and any indication of delivery behavior when the target agent is offline, which are the main things an agent could get wrong when invoking this tool.

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 100% schema description coverage, the baseline is 3; the schema already documents title, body, agent_id, and agent_name including lengths and the login-name pattern. The "Plain text only" line adds a mild formatting constraint for body not stated in the schema, but the description never clarifies the relationship between agent_id and agent_name (neither is required, suggesting one-or-the-other) — a meaningful omission given those are the addressing 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?

The description opens with a specific verb and resource ("Show a notification to an agent in the CRM") and scopes it as internal-facing rather than customer-facing, which is exactly the axis that separates it from siblings like send_sms or call_text. It stops short of naming a specific alternative sibling, so distinctness is conveyed indirectly rather than explicitly.

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 exclusion "This doesn't contact a customer" is useful negative guidance, telling the agent this is not an outbound communication tool. However, there is no explicit statement of when to prefer this over crm_add_note or crm_schedule_callback, so the when-to-use decision is only implied.

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