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

Annotations already cover read-only/idempotent/non-destructive/closed-world, and the description adds substantive traits beyond them: over-coverage semantics ('The range may allow or block additional addresses'), normalization and overlap-counting behavior, and a data-handling note that inputs are submitted to this server with no outbound network requests. The over-coverage caveat is a real behavioral consequence an agent must know before using the result.

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?

Front-loaded with 'Use when ...' and organized around usage, inputs, and outputs; every sentence carries content. It is dense and restates a few schema facts (1–1,000 items, 64 characters) that the schema already enforces, which costs a little efficiency.

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, so return details need not be explained, yet the description still names the returned fields (canonical CIDR, inclusive range, decimal-string counts, additionalAddressCount) and covers input constraints, semantics, and exclusions. Nothing needed to call this single-parameter tool correctly is missing.

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%, so the baseline is 3, but the description adds meaning beyond the schema: the cardinality range (1 to 1,000), the single-address-family constraint, host-bit normalization, and that overlaps are counted once. Only the 'count overlaps once' semantic is genuinely new information, but it is decision-relevant for correctness of the count.

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 states a specific verb+resource ('combining ... into one smallest covering CIDR') and immediately narrows the scope with 'This computes one CIDR for the supplied inputs; it does not optimize an entire list against an entry limit or change firewall rules.' That distinction separates it from cidr-subtract (set difference) and any firewall-mutating tool, so an agent can identify the tool's job without opening the 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?

It gives explicit trigger conditions ('Use when combining a selected group of firewall allowlist or blocklist entries into one smallest covering CIDR, or when checking the exact extra coverage') plus negative guidance (does not optimize against an entry limit, does not change rules). It stops short of naming sibling tools like range-to-cidrs as the alternative for full-list conversion, so routing is clear but not fully disambiguated.

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