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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false and openWorldHint=false, yet the description still adds genuine context: determinism, no network access, no stored state, and concrete limits (64 KB input, 1 s per call, 1 MB result, max 1,024 subnets). That is useful operational detail beyond the structured fields, though it does not describe error behavior for invalid prefix values.

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 purpose is front-loaded and the ES/EN duplication is at least structured, but the 'When:' enumeration is a long, mostly irrelevant list that inflates the definition without helping this tool. The useful sentences (purpose, exclusion, limits) are a small fraction of the text.

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 an output schema present, return values need not be explained, and the description covers purpose, sibling exclusion, side effects, determinism and resource limits. The one real deficiency is that the usage guidance is generic template text rather than guidance specific to splitting CIDR blocks.

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% (both params documented with examples and bounds), so baseline is 3. The description earns an extra point by implying the semantic constraint that new_prefix must be longer than the input block's prefix and that output is capped at 1,024 subnets — information the schema's 0–128 range does not convey.

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 and resource with scope: 'Divide un bloque CIDR en subredes iguales de un prefijo mayor (máx. 1.024)'. It also explicitly names the sibling it is not ('No para: describir un bloque CIDR IPv4/IPv6 (cidr-info)'), so an agent can separate it from cidr-info without opening a schema.

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 exclusion is explicit and correct ('Not for: describing an IPv4 or IPv6 CIDR block (cidr-info)'), which is real routing value. But the positive 'When:' clause is largely boilerplate borrowed from unrelated tools (URLs, HTTP headers, tokens, version strings, HTML/Markdown documents) and only 'IP range' actually applies, so the guidance an agent needs for this tool is muddied.

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