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

With no annotations provided, the description takes on full disclosure responsibility. It reveals the auth requirement (X-Org-Api-Key), the return shape (from, to, at, by, method), and a security-driven limitation (delivery cannot be performed via MCP). It omits behavior around conflicting to_state/action inputs or error handling, but the essential behavioral traits are covered.

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 longer than average but every sentence carries operational weight: purpose, parameter modes, conditional requirement, security restriction, return fields, and auth. It is front-loaded with the core purpose and flows logically, though a slight trim could improve scannability.

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?

Given 9 parameters, no annotations, and no output schema, the description provides a solid operating picture: what the tool does, valid states/actions, a special-case requirement, an explicit exclusion, return fields, and authentication. It misses some parameter nuances (evidence, delivery_type) and edge cases (conflicting inputs), but is generally complete for safe 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?

The schema has zero description coverage, so the description must compensate. It thoroughly explains to_state and action (including valid values) and clarifies the no_show_type requirement. However, it leaves evidence, delivery_type, notes, and apiKey meanings implicit, and it does not fully clarify the relationship or precedence between to_state and action.

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 clearly states the tool executes a state transition on a session, distinguishing it from sibling read tools like lifecycle_get_state and lifecycle_history. It enumerates valid states and semantic actions, and even includes a specific exclusion (delivery) with rationale, making the tool's scope unmistakable.

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 explicitly tells the agent when not to use MCP (for delivery) and directs to the REST endpoint, and it specifies that no_show_type is required for the no_show state. However, it does not explicitly contrast with lifecycle_get_state/history as the read alternatives, though the tool name and purpose make this inference fairly clear.

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