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

Annotations establish mutation and non-idempotency; the description adds the non-obvious replacement semantics ('omitted filters are cleared') and the async readiness gate, which are real behavioral facts beyond structured data. It stops short of naming search.get as the way to verify readiness or describing failure modes, so not a 5.

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, each carrying a distinct load: substitution rule, field semantics, precondition. The most consequential constraint (clearing omitted filters) is front-loaded after the identity statement.

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?

A mutation tool on a nested 6-parameter schema; the description covers identity, replacement semantics, the input/query split, and readiness. Return values are covered by the output schema, so the only residual gap is how to check readiness before calling.

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?

With 50% schema coverage, the description compensates for the most important ambiguity by defining input vs. query as mutually exclusive and by flagging wholesale replacement on omission. It does not add meaning for page/view/sort, which the schema already annotates or enum-restricts.

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 (update) and resource (existing search), and explicitly contrasts it with the sibling behavior of creating another search. An agent can distinguish this from search.create without opening either schema.

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?

Gives the selection condition versus search.create ('instead of creating another'), the parameter contract ('input OR the complete replacement query'), and a state precondition ('wait until the current search is ready or failed'). Nothing essential is left to inference.

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