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

Annotations indicate a non-read-only, non-idempotent, open-world mutation, but the description adds concrete behavior: append semantics, the 500-cap, and duplicate skipping. These details are not covered by the annotations and help the agent predict side effects accurately.

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, front-loaded with the core action and constraints, then a clear usage directive. No fluff or repetition of schema details beyond the necessary limit reference.

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 simple two-parameter mutation tool with a fully described schema, the description covers the essential usage context, behavioral notes, and input provenance. No output schema exists, but none is required for an action that returns a success/failure. The agent has enough to call it 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 coverage is 100%, so all parameters are documented. The description adds value by stating the duplicate-skipping behavior and the source of lead rows (search_b2b_leads/find_email), which is not in the schema. The 500 limit is redundant with maxItems but the usage hint is extra.

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 uses a specific verb ('Append') and resource ('to a list'), and immediately clarifies the key constraints (500 max, duplicate skipping). It also distinguishes itself from siblings like create_list or delete_list by focusing on adding leads, and explicitly ties to search_b2b_leads/find_email outputs.

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?

Provides a clear directive: 'Use this to save rows returned by search_b2b_leads or find_email.' This tells the agent exactly when to invoke this tool versus alternatives. The 500-per-call limit also implies a batching strategy for larger result sets.

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