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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=false, so the safety profile is covered. The description adds genuinely useful non-obvious behavior: a partial-failure model where invalid rows are reported in a per-row import report and 'never fail the list.' It omits auth/permission requirements, but the partial-import contract is the most valuable fact here.

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 tight sentences, no filler, with the core action and the optional payload front-loaded and the return/error behavior trailing. Efficient, though the parenthetical field list is dense filler that the schema already carries.

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 5-parameter creation tool with no output schema, the description covers what an agent most needs: it creates a list, rows are optional, and the return is a per-row import report. Gaps remain around duplicate/already-existing list behavior, project_id meaning, and list-size limits, but the essential calling contract is present.

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 only 20%, so the description must carry weight. It enumerates the contact fields (phone_e164, name, first_name, language, time_zone, external_reference, variables), which largely restates the nested schema, and it omits consent_basis, the source enum, the 10,000-row cap and the 28-variable limit. It adds some mapping value but does not compensate for the 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?

States a specific verb and resource ('Create a contact list in the workspace') plus the optional payload ('optionally with rows'), so the agent knows exactly what is produced. It does not, however, distinguish itself from the sibling add_contacts, which an agent could easily confuse with row insertion.

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 only implied: the phrase 'optionally with rows' hints that this tool can create an empty list that contacts are later added to, but the description never states when to pick this over add_contacts or when a list already exists. No exclusions or alternatives are named.

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