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

Adds genuine behavioral detail beyond annotations: never records consent, refuses a list_id naming a deleted or different list, and the static-vs-dynamic nature of the result. However, it asserts 'Idempotent (re-running adds nobody twice)' while the annotations declare idempotentHint=false, so the description contradicts structured data on a trait an agent would rely on when deciding whether a re-run is safe. The contradiction caps this score despite the otherwise useful disclosure.

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?

Three tight sentences: core behavior first, then the static/idempotency/refusal caveats, then the alternative. Every clause carries information an agent needs to choose and call the tool; no padding.

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 mutation tool with nested rule trees and no output schema, the description covers the important semantics: snapshot semantics, idempotency claim, refusal behavior, and consent. It does not say what the call returns (e.g., resulting list id or member count), which is the main loose end for an agent planning a follow-up step.

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 80%, so parameters are largely self-documented. The description's only added semantic is that list_id is 'for a new list', which the schema's own description already states verbatim; nothing is said about how rules/exclude_rules drive the saved membership beyond what the schema documents.

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 ('save who a find_people rule matches now as a STATIC list'), names the source rule tool, and explicitly distinguishes itself from the dynamic-list alternative (edit_email_campaign librarySaveAudience). An agent can separate this from find_people and build_list_from_events without opening a schema.

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 the when ('save who a rule matches NOW'), the when-not ('for a list that keeps itself up to date'), and names the sibling plus the exact parameter to use instead ('librarySaveAudience with the same rules'). This is the explicit when/when-not/alternative pattern.

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