update_manifest

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

With no annotations supplied, the description carries the full behavioral burden, and it discloses the single most important trait: the operation saves only and never submits to CBP, plus the consequence that a previously submitted manifest needs manual re-submission. It stops short of covering reversibility, whether omitted fields are preserved, or how already-submitted manifests behave on edit.

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 mutation scope and immediately followed by the critical non-obvious constraint. No filler and nothing buried.

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 no-annotation mutation tool with a nested schema and no output schema, the description covers what changes, what does not happen (no CBP submission), and the follow-up consequence. It lacks any note on partial-update semantics or the result of the call, which keeps it shy of a 5.

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 maps loosely onto the top-level parameters (flight fields, add occupants, remove occupants) which helps orient the agent. With schema coverage around 50% and a deeply nested object of flight fields, duty enums, and occupant identity options, the description adds no detail beyond that coarse mapping — the specifics live in the schema or nowhere.

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 gives a specific verb and resource ("Change a manifest") plus an enumeration of what can be changed: flight fields, occupants added and/or removed. That is far more concrete than the bare name. It does not, however, name a sibling such as create_manifest_draft or get_manifest, so the agent must infer the boundary from the name alone.

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?

Usage is implied by the "Change a manifest" framing and the note that an already-submitted manifest must be re-submitted manually, which tells the agent this is the edit path for an existing manifest. There is still no explicit statement of when to use this versus create_manifest_draft or get_manifest, and no stated prerequisites such as the manifest needing to exist.

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