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

Annotations already establish readOnly, idempotent and non-destructive, so the safety profile is covered; the description adds real behavior beyond that by disclosing ordering (newest first), the three source systems whose data is merged, and the lookback default. It does not say how many records come back or what a limited result set looks like, which is the main remaining gap for a retrieval tool.

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 sentences, front-loaded with what is returned, then the use case, then the parameter rule — no restatement of the title or filler. The HEL-498 ticket reference is minor internal noise but does not cost a sentence of clarity.

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 and a low schema-coverage input, the description carries the burden well by describing the content and ordering of returned records and the sources they come from. It is only incomplete on result volume/pagination and on what an empty history implies.

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 coverage is only 33%, so the description must compensate, and it does for the least-documented parameter: window_days is explained as a lookback with a 1–180 range and a default of 30 that appears nowhere in the schema. The fields parameter is covered by the schema itself, but contact_id receives no semantic explanation at all, leaving one gap.

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 names a specific verb (get) and a precisely scoped resource: cross-channel history for a contact, ordered newest first, drawn from call summaries, voice campaign outcomes and WhatsApp campaign messages. It clearly distinguishes this from a plain contact lookup by describing prior-interaction history, though it does not name a specific sibling tool it differs from.

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?

"Read only; use it to answer 'what happened with this customer before'" gives a clear context for invocation rather than just restating the name. What is missing is an exclusion or alternative — e.g. when to use list_call_history or contact_conversations instead — so it stops short of full when/when-not guidance.

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