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

Annotations already declare readOnly, idempotent, closed-world and non-destructive behavior, so the description's job is to add context. It does: an audience/eligibility constraint ("Current clients only") and a critical disclaimer that the returned plain-language figures are not authoritative ("The policy documents are the binding contract"), which matters because an agent may otherwise present the summary as legal fact.

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, front-loaded with the eligibility constraint and scoped in the second. No wasted wording, though the fragments read more like terse notes than a coherent instruction and "in plain words" is slightly informal for a specification.

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?

The tool is simple — two required string parameters, no output schema, no nesting — and the description covers audience and the non-authoritative nature of the result. What it omits is any explanation of the two required inputs and any indication of what the summary contains (limits only? perils? deductibles per coverage?), which matters given 0% schema description coverage.

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 0% for both required parameters, so the description carries the full burden. It hints that one policy is involved (policy_id) and that the caller must be a current client (client_session), but never explains what a client_session value is, where it comes from, or its format — leaving the required session parameter effectively undocumented.

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?

"Limits and deductibles for one policy in plain words" gives a specific resource and an explicit scope (one policy), so the agent knows this returns a human-readable coverage summary rather than raw policy data. It does not differentiate itself from siblings like get_policy_details, which an agent would have to reason about on its own.

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?

"Current clients only" functions as an implied eligibility gate that tells the agent when this tool applies (existing clients, not prospects). However, there is no explicit routing against alternatives such as get_policy_details or get_document, leaving the agent to infer which tool answers a coverage question versus a full policy lookup.

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