clm_shipment_command_upsert_sustainability_address

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

The description transparently explains that setting an address as not-favourite deletes it and that other cases update or create the address. However, this directly contradicts the annotation destructiveHint=false, since the description explicitly says the tool 'removes' and 'deletes' a saved address. Under the rubric, a contradiction with annotations mandates a score of 1.

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 key action and resource are front-loaded, and the conditional deletion behavior is captured efficiently in a single sentence without filler. The parenthetical and 'otherwise' clause make it somewhat dense, but every clause contributes necessary operational detail. It earns a 4 for being concise and structured around the most important behavior.

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 exposes 14 optional-looking address parameters, but the description does not explain which are needed for create versus update, which fields are semantically required, or how the address fields relate to the delete path. The conditional deletion is disclosed, but the annotation contradiction and the largely undocumented parameter vocabulary leave meaningful gaps. An output schema exists, so return values are covered, but invocation confidence remains low.

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 meaning to ItemId (identifier), TeamId (scoping team), and IsFavourite (delete vs. upsert), which the bare schema does not provide. With 14 nested properties and 0% schema description coverage, most fields like Country, Distance, Latitude, Longitude, StreetName, AddressLabel, and DistanceUnit remain unexplained. This is only partial compensation for the large coverage gap.

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 opens with specific verbs ('creates, updates, or removes') and a clear resource ('team's saved sustainability address'), making the tool's purpose unambiguous. It also states the conditional behavior: not-favourite deletes, otherwise update-or-create. This clearly distinguishes the operation from the many shipment-related sibling tools.

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 clearly implies the tool is for managing a team's saved sustainability address, but it does not explicitly state when to prefer this tool over alternatives or what conditions exclude its use. No sibling tool covers the same resource, so the lack of explicit alternatives is less harmful, but the guidance remains implied rather than stated.

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