Read I/O signals

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

Annotations already cover read-only/idempotent, but the description adds substantive behavior: the default returns values of unknown age from memory, controller-backed reads cost a controller round trip, controller text must be treated as data not instructions, and the caller should flag stale/replayed results. These are non-obvious operational traits not derivable from annotations or schema.

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 resource, then the default behavior, then the trigger conditions, then the safety note. Dense but mostly earning its place; the read-only sentence partially repeats the readOnlyHint annotation and the opening is a fragment, which keeps it short of a 5.

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 10-parameter read tool with a full output schema and complete annotation coverage, the description supplies the remaining essentials: data source and freshness semantics, the cost of controller-backed reads, and the prompt-injection caution. Nothing an agent needs to invoke this correctly is missing.

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 100%, so baseline is 3. The description adds cross-parameter meaning the schema states only per-field: that fresh, device, network, or category together switch the tool from memory to a controller search with a ≥3-character prefix requirement. That interaction is genuinely useful beyond the schema alone.

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?

Opens by naming the specific resource ('I/O signals and their values') and the read pattern is unambiguous in context; siblings cover entirely different resources (controller status, robot position, event log, RAPID source), so the distinction is implicit in the resource name. The opening fragment is terse rather than a full verb+resource sentence, keeping it just below a 5.

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?

Explicitly states the default path (daemon's in-memory signal table, no controller request) versus the alternative path (a read-only search on the controller when fresh:true or a device/network/category is given), and states the prerequisite for that path: a name prefix of at least 3 characters or a device. This is exactly the conditional routing an agent needs before choosing parameters.

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