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

No annotations are provided, so the description carries the full burden of behavioral disclosure, and 'Bytes to KiB' discloses nothing: no rounding/precision behavior, output format, or handling of invalid input. The schema parameters mention behaviors like 'discarded after the shape check' and 'no disk access', but these attach to unrelated inputs, not to the described conversion.

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 words constitutes under-specification, not conciseness; the description carries none of the explanatory load expected for a 10-parameter tool. Being short is the only structural virtue, and it earns little credit.

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 10 optional parameters, no annotations, and no output schema, the description must do heavy lifting but does none: no input mapping, no return format, no edge cases. An agent cannot correctly invoke this tool based on the provided definition.

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%, which normally sets a baseline of 3, but the parameters (git ref, URL, city, RSS feed, host, JSON, path, timezone, query, website) are semantically unrelated to a bytes-to-KiB conversion, and none could plausibly be the byte value. The description adds zero mapping or guidance, so an agent cannot determine what to pass.

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 'Bytes to KiB' essentially restates the tool name bytes-kib; it only clarifies the conversion direction. It is a bare label rather than a statement of function, and it fails to connect to any of the 10 schema parameters, none of which plausibly holds a byte quantity.

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?

There is no guidance on when to use this tool versus the 30+ siblings (e.g., calc-eval), no exclusions, and no context about input requirements. The only implied usage is a generic unit conversion, which is far too thin given the unrelated optional parameters in the schema.

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