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

Annotations already declare the write/idempotent/open-world safety profile, and the description adds real context beyond them: plan-limit gating, that refresh cadence is driven by existing platform jobs with no custom schedule promised, and idempotency-key reuse guidance. These are meaningful behavioral traits not present in the structured fields.

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?

Three short sentences, purpose front-loaded, no filler. Each sentence carries distinct information, though "Reuse idempotencyKey" is terse enough to need inference about why reuse matters.

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 described, and the mutation's cadence/limit behavior is covered. However, with 5 undocumented required parameters and no link to search_advertisers for obtaining the advertiser, the definition is only adequate for a creation tool.

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% across 5 required params, so the description must carry the load. It clarifies that advertiserId/advertiserName must reference a previously selected public advertiser and explains idempotencyKey reuse, but says nothing about the source enum (meta/tiktok) or format expectations for the other fields.

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+resource ("Create a watch") scoped to "a selected public advertiser" within a brand's plan. The verb alone distinguishes it from delete_ad_watch, get_ad_watch and list_ad_watches, so no explicit sibling naming is needed. Clear but not maximally differentiated.

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?

It gives a precondition ("within this brand's existing plan limits") and implies the advertiser must already be selected, but never says when to use this versus list_ad_watches/get_ad_watch or how to obtain a valid advertiser. Usage is implied rather than spelled out.

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