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

Annotations already establish idempotent, non-destructive mutation semantics, so the description's job is to add context beyond that—and it does, noting that companyAddress is appended to the unsubscribe footer on campaigns lacking one and is legally required in some markets, plus that designSpec feeds AI generation prompts. It omits whether unspecified fields are preserved or cleared, which for a 0-required-param update tool is a notable gap.

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 with zero filler, and the core action is front-loaded before the field semantics. It is dense but each clause carries information an agent needs; it loses a point only because the field-level detail could have been structured as a short list.

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 9-parameter, 0-required, no-output-schema mutation with rich annotations, the description supplies the non-obvious semantics for the highest-impact fields and flags a legal side effect. Remaining parameters (logoUrl, fontFamily, colors) are self-describing in the schema, so the overall picture is complete enough to call safely, missing only explicit partial-update behavior.

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 89%, so the baseline is 3; the description earns above that by explaining the semantic role of designSpec (a Markdown DESIGN.md that steers AI prompting, with voice/rules guidance) and confirming the merge-tag targets for companyName, websiteUrl, and companyAddress. These add real meaning beyond the terse schema descriptions.

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 ('Update workspace brand settings') that an agent can immediately map to a configuration mutation, and implicitly contrasts with the read-only sibling get_brand. It doesn't explicitly name that sibling or scope which fields are typically updated together, so it stops short of full sibling differentiation.

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 explains what the designSpec field is for and how company fields interact with merge tags, which guides usage, but it never states when to call this versus get_brand or the other update_* tools, nor whether partial updates are acceptable. Usage is implied by the field explanations rather than stated.

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