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

The description goes well beyond the sparse annotations (readOnly=false, idempotent=false, destructive=false) by disclosing meaningful behavior: the model is validated against the pricing layer before creation, name collisions with system-scope generators are rejected, and the operation is non-idempotent because re-deploying appends a new version. This gives an agent an accurate mental model of side effects and failure modes.

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?

The description is organized into three clear blocks: purpose, versioning/scoping rules, and validation behavior. It is slightly long, but every sentence earns its place—there is no fluff or repetition of the schema. The most decision-relevant facts (create vs. append, system-scope collision, token requirement) are front-loaded.

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?

Given the moderate complexity (nested payload, optimistic concurrency, scope constraints), the description covers the essential operational context: what it returns (version, version_token, config_hash, etc.), why it can fail (platform scope collision, model validation), and how it interacts with sibling calls (list/get for tokens). It doesn't spell out the exact return schema, but the description references the return fields adequately for an agent to proceed.

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?

The schema already gives each parameter a descriptionhare and even adds a note explaining version_token semantics and deploy-time validation of model. It adds value on top of the schema by explaining exactly when expected_version_token is required (new vs. existing generator) and what a 'model must resolve to an authoritative price' means in practice. Minor gap: the description does not elaborate on generation_contract values beyond the schema's one-line summary, but the schema carries that load.

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 opens with a specific verb ('Deploy') and resource ('image generator'), then immediately states the core behavior: generators are created or versioned. It also answers 'what is this for' by explaining that skills reference generators to route image-generation calls to a model. This is unmistakably distinct from sibling tools like revoke_image_generator or list_image_generators.

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?

Clear operational rules are given: first deploy creates version 1, re-deploys append a version and require expected_version_token, and the token is obtained from deploy/list/get calls. There is also a concrete exclusion rule ('cannot deploy a new generator whose name matches an active platform-scope generator'). An agent knows exactly when and how to invoke this tool versus alternatives.

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