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

Annotations declare the write/not-readOnly and non-destructive profile, and the description adds meaningful context beyond them: 'Nothing here is ever published', short-text dropping, duplicate skipping, and the deduplication/palette caveats. It stops short of describing response or failure behavior, but adds real value over the annotations.

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?

A single dense paragraph with no filler; the 'what to add' framing comes first, followed by constraints, routing, and the follow-up call. Slightly long, but nearly every sentence carries operational value.

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 6-parameter, all-optional write tool with no output schema, the description covers sourcing rules, quantity guidance, targeting, deduplication behavior, and the required follow-up step. It leaves the return shape unstated, but with no output schema that is a minor gap.

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 already 100%, so the baseline is 3, but the description adds genuine meaning: accountId attaches to one account vs omitting for workspace-wide style, and imageUrls must be real posts (not screenshots, which poison the palette). It also explains why transcripts matter for video accounts, going beyond the schema text.

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: add customer-supplied style material (captions, transcripts, images) so the style can be learned from it. It is clearly distinguishable from siblings like import_style_from_link, learn_brand_style, and delete_style_examples, and it names the source constraint (accounts not connected to Ignix).

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?

Explicit about when to use and what qualifies: content from unconnected accounts, ~10 texts minimum and 20 plenty, transcripts being the only way for video accounts. It also routes the agent to the next step ('call learn_brand_style so the style picks it up') and explains the accountId-vs-omit choice.

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