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

Annotations already declare this a read-only, non-destructive, open-world list operation, and the description still adds useful context: the required 'configuration' scope, the underlying endpoint, and the pagination contract (pass next_offset as offset). It doesn't mention error behavior or ordering defaults, but the safety profile is fully 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?

Four short sentences, front-loaded with purpose, then scope requirement, then endpoint, then return/paging shape. Nothing is redundant or padded.

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?

No output schema exists, so the description carries the return contract and does so (count, total, next_offset, items) plus the auth scope. For a parameterless-required read-list tool, an agent has everything needed to call and page it correctly.

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 coverage is 100%, with each of the six parameters (q, sort, with, limit, filter, offset) documented in-schema, including next_offset paging. The description restates the paging mechanism but adds nothing new about filter/sort syntax, so baseline 3 applies.

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 ('List the units') and immediately disambiguates them by role: the ids an invoice position's unit_id refers to, with concrete examples (piece, hour). That distinguishes it from nearby list tools such as list_cost_units and list_services.

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 phrase 'which an invoice position's unit_id refers to' tells the agent exactly when to call it: resolving unit ids to labels. It does not say when to prefer a sibling list tool or whether units are ever created/edited elsewhere.

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