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

Annotations already declare this is a non-destructive, non-idempotent, closed-world mutation. The description adds a genuinely non-obvious behavioral fact not in any structured field: the operation is free and cost is deferred to generate_adaptations. It does not disclose duplicate-handling or what happens on repeated creation, but the cost disclosure is real added value.

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, with the action and its inputs front-loaded and the cost caveat placed second where it reads as a qualifier rather than a preamble.

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 an 11-parameter mutation with a nested language_choices object and no output schema, the description is thin: it omits any mention of the localization modes (bilingual/code-switch, visual text mode) that are the tool's main complexity. An agent could call it correctly on required params, but would have no basis for deciding whether to set language or visual options.

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 55%, so the description must carry some weight; it does map "source ad copy" to primary_text and "target audiences" to audience_ids, aligning with the two required semantic groups. However, it says nothing about language_mode, language_choices, visual_text_mode, or cultural_moment_id — the parameters most likely to confuse an agent — leaving them to bare enums and defaults.

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 campaign project") plus the two core inputs it wraps (source ad copy, target audiences), which distinguishes it from read-only siblings like list_projects. Differentiation is only partial — it never explicitly contrasts with the other creation-adjacent tools such as create_workspace or generate_adaptations beyond naming the latter as a follow-up.

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 sentence "no credits are spent until generate_adaptations is called" implies a workflow ordering (create here, then generate), which is useful, but it never states when this tool is the right choice versus its siblings or what prerequisites exist (e.g., brand/audience must exist first). 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.