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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds non-obvious behavioral context beyond the annotations: it explicitly states that reading does NOT trigger a provider refresh, which is exactly the kind of operation-scope detail an agent needs.

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, zero filler. The primary purpose is front-loaded and the refresh caveat follows immediately. Every clause earns its place.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. The description supplies the key non-obvious fact (no refresh triggered) and what's listed. Adequate for a simple one-parameter list tool, though a brief note on ordering or pagination would fully close it.

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 0% for the single brandId parameter, but the single required parameter is largely self-describing. The phrase 'this brand's' implies brandId scopes results to a brand, adding marginal meaning, but no format or scoping detail beyond what the schema name conveys.

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+resource ('Read this brand's saved advertiser watches') plus an extra data element ('last refresh timestamps'), so the agent knows exactly what this returns. It implicitly distinguishes from create_ad_watch/delete_ad_watch, though it doesn't explicitly contrast with the singular get_ad_watch sibling.

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 statement 'Does not trigger a provider refresh' is implicit usage guidance – it tells the agent this is a safe read that won't cause side effects – but there is no explicit when-to-use rule or named alternative (e.g., get_ad_watch for a single watch). Usage is implied rather than stated.

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