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

With no annotations and a description that only restates the name, the description fails to disclose any behavioral traits: whether the tool performs network calls, validates input, normalizes data, or simply returns the current time. The presence of a 'json' parameter described as 'discarded after the check' suggests validation behavior, but the description doesn't mention it. This is a severe lack of transparency for a tool with such a misleading name.

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?

The description is extremely short, which is normally a positive trait for conciseness, but here it is under-specification rather than concise efficiency. 'Current UTC timestamp' is a single fragment that cannot be considered a well-structured description. It earns the low end because it wastes the reader's time by providing no actionable information beyond the name.

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?

Given the complexity of a tool with four unrelated parameters, no required fields, no output schema, and no annotations, the description is severely incomplete. An agent cannot determine what the input parameters do, which are needed for the intended use case, what the return value looks like, or how this tool relates to sibling tools like 'citation' or 'domain-shape'. The definition fails at every level of contextual completeness.

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?

Although the schema has 100% description coverage for each parameter, the description contributes nothing to parameter semantics. The tool is named 'utc-time', yet its schema includes four unrelated parameters (url, host, json, zone) with descriptions that do not connect to time retrieval. The descriptions say 'HTTPS URL to normalize or cite', 'Public hostname', 'JSON text to validate', and 'IANA timezone name'—none clarify how these relate to obtaining a UTC timestamp. The schema may document each parameter individually, but the tool-level meaning is completely absent.

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 'Current UTC timestamp' is a tautology—it restates the tool name without specifying what action the tool performs, what input it expects, or what output it produces. The input schema contains four unrelated parameters (url, host, json, zone), none of which are marked required, creating a glaring mismatch between the description and the actual invocation interface. An agent cannot determine what this tool does with any of these parameters.

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 provides zero guidance on when to use this tool or how it differs from siblings like 'citation' or 'compatibility'. There is no mention of which parameters are relevant for obtaining the UTC timestamp, nor any exclusion criteria. The agent is left to guess whether all four unrelated parameters are needed, optional, or ignored.

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