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

Goes well beyond the annotations: discloses asynchronous execution with a `building` status and polling instructions, states that existing records are retained, requires user approval and confirmed=true, and warns that writes are never retried automatically. These details complement the destructiveHint and non-idempotent annotations without contradicting them.

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?

Front-loads purpose, then layers behavior, async polling, and approval requirements in a tight sequence. Every sentence carries operational value: scope, additive behavior, async status, polling, approval, and retry policy. No filler.

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, but the description explains the response (the list with status `building`) and how to poll to completion. It also covers approval prerequisites and retry semantics, making it complete for an agent to call this destructive, asynchronous mutation 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 description coverage is 33%; the nested filter and location parameters are documented in the schema itself with useful property-level descriptions. The description mentions filters, locations, and confirmed=true in prose but does not add meaning for add_as_prospects or prospect_search_id, leaving some parameters unilluminated beyond the schema.

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 description states a specific verb and resource (build a list) and the precise scope: add records matching given filters and locations to this list. It also distinguishes the operation from siblings implicitly by describing filter-driven building rather than adding specific items (list_add_items) or creating a list (list_create). An agent can tell what this does without opening the 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?

Clear guidance on behavior: existing records stay, building again adds to the list, and user approval with confirmed=true is mandatory before changes or credit use. It does not explicitly name alternative siblings (e.g., list_add_items for explicit items vs. this tool for filter-based builds), leaving a small gap in when-to-use vs. what-not.

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