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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds a behavioral constraint: the diff is executed against locally cached, integrity-verified catalogs, implying no network fetch and a verification step. This complements the annotations and clarifies the operational boundary.

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 a single sentence that immediately front-loads the core action and constraint. There is no filler or redundant wording.

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 tool with a deeply nested `stack` parameter, no output schema, and no parameter descriptions, a single sentence is insufficient. The agent is left to infer what 'diff' produces, how the local cache is selected via `toCatalogDigest`, and what constitutes a difference. The complexity demands more explanatory context.

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 explain the semantic role of `stack` and `toCatalogDigest`. It only references 'a stack' and 'catalogs' generically, giving no detail on how `toCatalogDigest` identifies the catalog or which fields of the stack are used. It does not compensate for the absent 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?

The description uses a specific verb ('diff') and a resource ('a stack'), and the qualifier 'only against locally cached, integrity-verified catalogs' differentiates it from likely siblings such as inspect_stack or compose_stack. An agent can tell this is a comparison operation against local, verified data rather than a fetch or validation tool.

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 phrase 'only against locally cached, integrity-verified catalogs' implies a specific context—comparisons should use local, verified data—but it never names sibling tools or states when not to use this tool. This is an implied use case, leaving routing to inference.

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