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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that only distinct keys are returned and that is_complete signals truncation, which is genuinely useful behavior beyond annotations, but the pagination statement is garbled ('more than one call lists') and there is no cursor parameter in the schema, leaving unclear how further calls differ.

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 purpose is front-loaded in one efficient sentence. The second sentence is ungrammatical and ambiguously worded, which costs clarity without adding length problems.

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 single-parameter read-only lookup this is close to sufficient, but with no output schema the agent is never told the return shape (bare array of keys versus an object wrapping keys and is_complete). The mention of is_complete implies a wrapper without confirming it.

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 0% for the single required parameter, so the description must carry the meaning. 'On a project's contacts' does scope project_id as the owning project, but nothing is said about format or whether it accepts IDs versus slugs.

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 distinct attribute keys on a project's contacts.' The phrase 'attribute keys' separates it from the nearby list_contact_tags sibling without naming it explicitly, so an agent can still confuse the two in edge cases.

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?

Gives downstream use cases (audience filters, branch conditions, merge tags) that imply when to reach for this tool, but offers no explicit exclusions or named alternative such as list_contact_tags for tag-based filtering. The is_complete note hints that repeat calls may be needed but does not say how.

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