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

Explains exactly why readOnlyHint=false despite being non-destructive: it refreshes onboarding state and logs the Q&A into the conversation. It also bounds side effects ('sends nothing outside Aeroz', 'changes no product, shipment or passport data') and flags declined answers and non-legal compliance signals — context annotations cannot carry.

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?

Front-loaded with purpose and examples, then explains the grounded answer types — justified because there is no output schema. It is dense and somewhat long, but the parenthetical examples and definitions all earn their place; little could be cut without losing grounding semantics.

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?

Covers purpose, use cases, side effects, scope limits, and enumerates the `grounded` return values (records/knowledge/computed/model/declined) with where the evidence lives (chips, citations) — necessary since no output schema exists. An agent knows how to call it and how to interpret and relay the answer.

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?

Only one parameter at 100% schema coverage, so the schema already defines it and sets the 2000-char limit. The description adds that the question should be phrased in plain language as the person asked it, which is minor but real added meaning.

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 (ask) and resource (this org's dedicated Aeroz agent) and enumerates the classes of questions it answers — account state, records lookup, help topics. An agent can distinguish it from a plain data-fetch sibling like where_is or search without opening the 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 concrete example questions ('what do we still need to do', 'where is lot X') that make usage conditions vivid, and scopes reads to 'this key's read scopes'. It does not, however, say when to prefer siblings such as where_is, find_unit or search for the lookup-style questions it also claims to answer, leaving overlap to inference.

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