numfmt

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

Annotations already provide readOnlyHint: true. The description adds that it is 'Read-only, no side effects' and explains default output format (JSON envelope) and use of --raw for plain output. It also clarifies it parses human-readable strings back to raw numbers. No contradictions with annotations.

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 four sentences, starting with the primary action. Each sentence adds value: main purpose, read-only claim, parsing direction, use cases, and exclusion of printf. No unnecessary words, but could be slightly more streamlined.

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 10 parameters, no output schema, but full schema descriptions, the description covers main use cases and contrasts with sibling printf. It does not detail all parameters (e.g., encoding, precision) but those are in schema. This is sufficient for a tool that converts numbers.

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 baseline is 3. The description adds context for the raw parameter ('use --raw for plain output') and mentions parsing numbers implicitly. But it does not elaborate on other parameters like encoding or precision beyond schema, so it meets baseline without exceeding.

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 clearly states 'Convert numbers between plain, SI, and IEC unit systems.' It specifies the verb (convert) and distinct resource types (numbers between unit systems). It also distinguishes from sibling 'printf' by noting it is not for general formatted string output.

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 says 'Use to humanize byte counts or parse user-supplied size strings' and warns 'Not for formatted string output — use printf for general formatting.' Also references 'See also printf.' This gives clear when-to-use vs. when-not-to.

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