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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for adding failure semantics the annotations cannot: "not_ready" for unapproved instructions, "not_found" for no match, and the atomicity guarantee that it "never returns a partial agent." It does not address permissions/scoping on agents or any throttling, which keeps it out of 5 territory.

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 tight sentences, front-loaded with the action and the lookup mechanism, then failure modes. "Follow them exactly" is an instruction to the consuming model rather than a property of the tool, so it is slightly out of register, but it costs almost nothing in length.

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 tool is simple (two optional string params, closed-world, output schema present), so the description need not explain return payloads — and it correctly focuses on the error contract instead. The remaining gap is the mutual-exclusivity/omitted-parameter behavior, which matters given zero required parameters and no schema descriptions.

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 carry the parameter semantics and only partly does. It clarifies that agent_name must be an exact match, which is genuinely useful for a 0%-coverage schema, but it never states whether the two identifiers are mutually exclusive or what happens when neither is supplied despite required_parameters being empty.

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 names a specific verb and resource ("Load one of your Dactic agents") and states the outcome ("so you can run it in this chat: returns its complete instructions and skills"). That is far more than the title restates. It does not, however, distinguish itself from close siblings like get_agent or invoke_agent, which an agent would reasonably confuse it with.

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?

"so you can run it in this chat" implies the use context, and "by agent_id or exact agent_name" gives the two lookup modes. But there is no explicit when-to-use versus get_agent (inspect metadata) or invoke_agent (execute), nor guidance on which identifier to prefer when both are available. Selection against siblings is left to inference.

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