net_vlsm

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and the description earns credit for what annotations do not say: the exact return contents (subnet, mask, wildcard, gateway as first host, host range, broadcast per segment). That is genuinely useful because no output schema exists. It omits failure behavior when needs exceed the pool size, which is the main remaining gap for a mutation-free computation tool.

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?

One compact statement front-loads the operation, followed by the algorithm and the return shape; no filler sentences. The density is close to cryptic in places (`needs = {...}` with no framing verb), but nothing is redundant.

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 no output schema, listing the returned fields is the right compensation, and the `needs` example fills a real schema gap. Still missing: the required format for `pool`, behavior when the pool is too small for the requested segments, and any sense of output ordering beyond 'largest first'. Adequate but with clear gaps for a 2-parameter nested-input tool.

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 0% across both required parameters, so the description has to compensate. The example `{'Sales': 50, 'Eng': 25, 'R1-R2': 2}` is genuinely valuable — it shows `needs` is a name-to-integer-host-count map, which is not obvious from `additionalProperties: {type: integer}`. However, `pool` is never explained (format such as CIDR, address range, or prefix), leaving half the parameters undocumented.

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 names a specific operation and resource: a VLSM (variable-length subnet mask) plan computed from a pool plus per-segment host requirements. The inline example of the `needs` shape makes the intent concrete. It stops short of naming or contrasting with siblings such as net_subnet / net_split / net_summarize, so an agent must infer the boundary from the name alone.

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?

'Largest first' describes the allocation algorithm, not when to choose this tool over net_subnet, net_split, or net_summarize. There is no statement of prerequisites (e.g., pool must be large enough), no exclusions, and no alternative routing. The agent gets the mechanics but not the selection criteria.

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