create_manifest_draft

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

With no annotations at all, the description carries the full burden, and it does disclose the key behavioral trait: the manifest is persisted as a draft and is not sent to CBP. It says nothing about whether an id is returned for later update/submit, duplicate-manifest behavior, validation against CBP rules, or permission requirements.

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 short sentences, front-loaded with the action and its critical state qualifier, with zero filler. The second sentence exists only because the manual-submit constraint is non-obvious.

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 mutation tool with a rich nested schema, no annotations, and no output schema, the description covers the draft-versus-submit distinction but leaves the agent guessing about the response (is a manifest id returned?) — information needed to later call update_manifest. Adequate but with a clear operational gap.

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 100% and nested fields are individually documented, so the baseline is 3. The description adds no meaning about the two top-level parameters (fields, occupants) beyond what the schema already explains, such as occupant ordering intent or required-field minimality.

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 verb and resource (create a new manifest) and scopes it precisely as a DRAFT that is saved but not submitted to CBP/eAPIS. It does not name a sibling such as update_manifest or list_manifests to route the agent, relying on the natural create/update distinction instead.

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 parenthetical 'saved, NOT submitted' plus 'Submitting stays a manual step on flashpass.net' tells the agent this is the creation endpoint and that no submit tool exists, which prevents a wasted search. It stops short of stating prerequisites (e.g. whether flight fields must be complete before creation) or how it relates to update_manifest afterward.

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