Describe an IoT thing

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds crucial context beyond them: it discloses the untrusted-data fence around attributes and explains why (any principal with UpdateThing can write them). This is real behavioral context about data trust and write reachability that annotations don't cover.

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?

A single, dense sentence front-loads what the tool returns and then explains the one surprising trait (untrusted-data fencing). No wasted words, appropriate length.

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?

For a two-param read tool with full schema coverage and no output schema, the description covers return contents and the key trust caveat. It doesn't mention things like error behavior for missing things or whether include_groups affects the groups field naming, but the core is solid.

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 documents both thing_name and include_groups (including the default). The description adds no parameter-level syntax or format detail beyond what the schema already provides, so baseline 3 applies.

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 (Returns) and resource (registry record of one thing) and enumerates the exact fields returned (ARN, thing type, version, billing group, groups, attributes). This clearly distinguishes it from siblings like list_things (which enumerates) and get_device_shadow (which returns shadow state).

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?

The description implies usage by naming the single-thing scope versus the list_things sibling, but it never explicitly states when to use this versus alternatives like get_device_shadow or why one would pick this tool. Usage is only implied by the resource described.

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