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

Beyond annotations that already flag a destructive, non-read-only mutation, it explains that rules are replaced as a complete set, omitted fields are preserved, confirm:true is required to apply, and dry_run validates without changing data. It also discloses practical limits such as not being able to target a single campaign and custom-field handling in Mailercloud.

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 most important constraints are front-loaded in the first two sentences, and the rule details are relevant for this complex tool. However, the long single paragraph with dense semicolon-separated rule taxonomy is harder to scan than a structured list would be.

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 an eight-parameter update tool with nested rule semantics and no output schema, the description covers the update behavior, preview/confirm lifecycle, rule replacement, operator constraints, edge cases, and examples. An agent has enough context to construct and safely apply an update.

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?

Although the schema already has full parameter descriptions, the tool description adds substantial cross-parameter meaning: operator/value shape rules (is_known/is_unknown, any_of arrays, between objects, 1-200 day ranges), activity filter_by choices, and two worked examples. This materially reduces the chance of malformed rule payloads.

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 first sentence gives a clear verb and resource ('Change a segment') and immediately defines the partial-update model: only changed fields are supplied and omitted fields are retained. It also distinguishes viewing current rules via get_segment, so an agent can tell this is an update tool rather than a read or create tool.

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 explains when to omit fields, when to fetch the current rules, and the preview/confirm workflow. It does not explicitly state when to choose create_segment or delete_segment instead, so the sibling routing is clear but not fully spelled out.

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