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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, and the description explains exactly why: asking refreshes onboarding state and records the Q&A in the conversation, but 'sends nothing outside Aeroz and changes no product, shipment or passport data.' It also defines the grounded verdict values (computed/model/declined) and instructs honest relay of a declined answer — behavioral context well beyond the annotations.

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 the core purpose, then example questions, then the grounded semantics and side-effect disclosure. The example questions and grounded definitions all earn their place, though the passage is on the longer side for a single-parameter tool.

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?

With no output schema, the description carries the return-value burden and does so: it explains the grounded field and its three values. It also covers side effects (state refresh, conversation recording) and data-handling limits, so an agent has everything needed to call it and interpret the result.

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 exists and schema coverage is 100%, with the schema already specifying 'The question, as the person asked it (at most 2000 characters).' The description only adds the 'plain language' framing, which is marginal beyond the schema. Baseline 3 applies when the schema does the documentation work.

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 and resource ('Ask this organisation's dedicated Aeroz agent a question... and get a grounded answer') and frames the scope as anything a business human would ask their account manager. It is clearly distinguishable from siblings like agent_conversation (which it points to for history) and onboarding_status. The example questions make the remit 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?

Gives concrete context ('anything a human at the business would ask their account manager') plus five example questions, which effectively routes the agent to this tool for account-status questions. It also names agent_conversation as where the Q&A lands. No explicit when-not guidance is provided, keeping it short of a 5.

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