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

With no annotations, the description carries the burden and covers key behavior: non-mutating, recalculate is expensive, every response contains _request_id in structuredContent, and non-main-server containers yield tool_to_call: null plus manual_handoff. This goes well beyond the schema.

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?

Front-loaded purpose, compact behavioral notes, and a clearly separated server rule. Every sentence carries operational value and there is no redundant restating of schema fields.

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 the unusual multi-server behavior, recalculate cost, and response ID, and an output schema exists for return shape. It is complete for invocation, though the auth_token/container_hash mutual-exclusion detail is left to the schema description rather than the tool description.

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?

The description adds real meaning for recalculate (expensive fresh pass) and references the server_name condition, but schema coverage is only 33%. It does not add semantics for framework, auth_token, or container_id beyond what their names and types imply, so the compensation for low coverage is partial.

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?

States a specific action—return scoring-driven ordered guidance for the agent—with a distinct resource and adds the non-mutating qualifier. The server rule about create_login_link/manual handoff also differentiates this from plain read-only getters, so an agent can tell what this tool contributes.

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?

Gives explicit conditional guidance: recalculate=true only when a fresh scoring pass is wanted, and a clear server rule saying when to hand off manually instead of calling create_login_link. It does not explicitly contrast against other get_* siblings, but the context is strong enough to avoid misuse.

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