List / search devices

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value by warning that a full device document can be hundreds of KB and by defining the `total` field semantics. Return-shape detail beyond that is thin, but this is a read-only list tool with a low disclosure burden.

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-loads the purpose, then the operational rule (filter with query, always project), then examples in a compact bullet-like form. The three inline JSON examples are dense but each illustrates a distinct pattern, so little is wasted.

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 five optional parameters, no required fields, an output schema absent, and annotations covering safety, the description supplies the two things an agent most needs: how to filter and the size cost of not projecting. Paging behavior (skip/limit bounds) and sort are left to the schema, which documents them adequately.

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 100%, so the schema already documents all five parameters, including query operators and projection syntax. The description's query examples ($regex on _id, $lt on _lastInform, VirtualParameters path) largely restate the schema's own examples, adding only the 'stale devices' framing and the total/skip relationship noted in the schema.

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 ('List or search CPE/ONT devices known to the ACS') and even names the underlying endpoint (GET /devices). It does not explicitly contrast itself with the singular sibling acs_device, so an agent must infer the collection-vs-single distinction from the names alone.

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 actionable operating guidance: use `query` to filter, 'ALWAYS pass a `projection`' to keep rows small, and supplies three concrete query patterns including a stale-device case. It does not name an alternative tool or state when this tool is the wrong choice, so it stops short of full when/when-not routing.

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