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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false. The description adds valuable context beyond annotations: rebuild behavior when pointer or valueType changes, refusal conditions for alias (uniqueness/length), guard hiding values, and that omitted fields are preserved. It doesn't explicitly address the destructive nature or reversibility, but the rebuild and guard notes provide significant behavioral insight.

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 extremely concise, packed into a few sentences with no wasted words. Each clause adds a distinct piece of information (partial update, rebuild trigger, alias refusal, guard effect, request count). It is front-loaded with the core behavior and efficiently structured.

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 15 parameters, 80% schema coverage, annotations, and an output schema, the description covers the most critical behavioral nuances: partial update, rebuild cost, alias constraints, and guard effects. It leaves some gaps (e.g., tags replacement, sorting/filtering implications), but overall it provides enough context for an agent to call it correctly without exploring the schema extensively.

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 high (80%), so the schema already documents most parameters well. The description adds a few semantics: omitted fields are left as-is (partial update), and pointer/valueType changes trigger a rebuild. However, it doesn't elaborate on most of the 15 parameters, and the baseline of 3 is appropriate when schema does the heavy lifting.

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 states a clear verb (Change) and resource (an index), and specifies partial-update semantics ('fields left out are left as they are'). It is distinguishable from siblings like create_index, delete_index, and rebuild_index. It falls just short of 5 because it doesn't explicitly name a sibling for differentiation, though the operation is unambiguous.

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 implies usage through behavioral notes (e.g., '1 request', rebuild semantics), but does not explicitly state when to use this tool versus alternatives like rebuild_index or create_index. There are no exclusions or alternative redirections, leaving the agent to infer the right context from the operation type.

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