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

Adds value beyond the annotations: template inheritance semantics, mapping override precedence, that api_key is write-only and verified live with a specific 422 invalid_api_key failure, and that custom sources get no network API. The annotations already cover the safety profile (non-destructive, non-idempotent), so the main gap is minor tension with openWorldHint=false given the live API key verification call.

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?

Four sentences, front-loaded with the required-parameter fact, then template behavior, then the api_key failure mode, then the no-template fallback. Every sentence carries information an agent needs before calling.

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 33-parameter create operation with no output schema, the description covers the choices that actually determine the call: template vs custom, mapping overrides, and live key verification. The remaining gaps (postbacks, percentage fields, tags) are largely covered by per-parameter schema descriptions.

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?

With 88% schema description coverage the baseline is 3, and the description adds genuine meaning by framing the large sub*/cost/format/zone_id block as 'mapping fields' whose explicit values override template defaults. It says nothing about tags, group_id, postbacks, traffic_loss, payout_percent or postback_percent, so it does not fully cover all 33 parameters.

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 ('Create a traffic source') and immediately disambiguates by noting only name is required and what template_id does versus a custom source. It does not explicitly name update_traffic_source as the mutation counterpart, but the create/update split is unambiguous from the verb.

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 a real decision rule: use template_id to inherit provider, API capabilities and default mapping from list_traffic_source_templates, with explicit mapping fields overriding the template; without a template the source is custom and has no network API. That covers template-vs-custom selection, though it does not say when to prefer custom over a template.

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