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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description still adds real context beyond them: the pagination contract (stable ID cursor, default 50, max 100) and the important permission caveat that catalog entries do not confer generation authority. It doesn't say whether an empty catalog or invalid cursor errors, but that is a minor omission given the annotation coverage.

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, front-loaded with the resource and its scope, then the authorization caveat, then the pagination contract. Nothing is redundant; the caveat sentence earns its place for an AI agent that might otherwise assume catalogs imply capability.

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 both parameters are optional. For a simple paginated read, the definition is functionally complete; only cursor continuation semantics remain implicit.

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%, so the description must carry parameter meaning, and it does explain both: limit's default and maximum, and that cursor is a stable ID. It still omits how to obtain and round-trip the cursor and the minimum of 1, so it only partially compensates for the documentation gap.

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?

Specific verb+resource: "Read configured models available to this tenant." The resource (models) is distinct from the sibling catalogs_* tools (fonts, languages, music, transitions, voices), though the description never names that distinction explicitly. An agent can tell what it returns, just not why it would pick this over another catalog call.

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?

No when-to-use, prerequisites, or named alternatives. "Catalog entries do not grant generation authority" is a semantic caveat about the results, not guidance on selecting this tool, and nothing tells the agent how to continue when the cursor runs out or which sibling to consult for generation-capable data.

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