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

Beyond the annotations, the description discloses non-obvious and important behavior: a sent postbacks list replaces the stored list, a blank api_key preserves the existing key, a new key is verified live, and changing proxy_id re-verifies the key through the new proxy. These details materially help the agent avoid destructive surprises and understand side effects.

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 description is front-loaded and compact: one sentence states the operation, and two follow-up sentences cover the most important special cases. There is no wasted wording.

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 destructive 33-parameter update tool with no output schema, the description covers the most important behavioral edge cases and clarifies that the update is partial. It does not discuss permissions, required id handling, or omitted-field behavior beyond api_key, but annotations and the rich schema reduce the remaining burden.

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 high at 91%, so the schema already carries most parameter meaning. The description still adds valuable semantics for three critical parameters: postbacks replacement, api_key blank-versus-new behavior, and proxy_id re-verification.

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 gives a clear verb and resource: 'Edit a traffic source (partial).' It distinguishes update from creation by using 'Edit' and noting partial behavior, though it does not explicitly name sibling alternatives such as create_traffic_source or get_traffic_source.

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 implies usage for editing an existing traffic source and clarifies partial-update behavior, but it does not state explicit when-to-use guidance, prerequisites, or when to prefer a different tool. The field-specific notes are useful but do not fully substitute for usage routing.

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