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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, and the description still adds substantive context: no network access, no stored state, determinism, and concrete operational limits (64 KB input, 1 s per call, 1 MB result). That is exactly the beyond-annotation information an agent needs to size inputs and avoid misuse.

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 useful content (outputs, exclusion, limits) is front-loaded, but the text is bilingual-duplicated and the EN variant degenerates into a pointer ('[EN completo / full EN: inputSchema.description]'), so the agent reads the same material twice while the noisy 'Cuándo' list inflates length without adding selection value.

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?

An output schema exists, annotations cover the safety profile, and the single parameter is fully documented, so the description only needs to add scope, limits and the sibling exclusion — all of which it does. The remaining gap is the misleadingly broad usage list, which could lead an agent to call it on non-CIDR inputs thinking it parses arbitrary URLs or tokens.

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?

Only one parameter, and schema coverage is 100% with an example, a maxLength and a format hint in the schema itself. The description restates the same facts at a high level and adds no syntax guidance (e.g. host bits tolerance, IPv6 prefix conventions) beyond what structured fields already give, so baseline 3 applies.

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+resource ('Describe un bloque CIDR IPv4/IPv6') and enumerates exactly what is returned (network, broadcast, hosts, mask, wildcard, counts), which distinguishes it from cidr-contains and cidr-split. It loses a point because the purpose sentence is followed by an unrelated laundry list (URLs, tokens, HTML files) that muddies what the tool actually computes.

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?

Has an explicit 'No para: verificar si una IP está dentro de ... (cidr-contains)', naming the sibling and the distinguishing condition, which is the key disambiguation need here. But the 'Cuándo' clause is so broad (any URL, header, token, HTML/Markdown file) that it reads as boilerplate rather than a real selection rule, and other CIDR siblings such as cidr-split or ip-range-to-cidrs are not mentioned.

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