explain_config_diff

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

With no annotations provided, the description carries the full disclosure burden and exceeds it: it reveals that the operation is deterministic ('no model call'), locally contained ('nothing leaves the machine'), normalizes input ('strips volatile lines'), structures output ('groups changes by config section'), and augments it with risk tags plus rationale. This gives an agent a precise behavioral model with zero annotation support.

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?

Two sentences with no filler: the core purpose is front-loaded, and the second sentence packs only high-value operational details (supported vendors, normalization, grouping, risk tagging, determinism, privacy). Every clause earns its place and the colon-delimited list is easy to scan.

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?

There is no output schema, but the description compensates by describing the return experience: plain-English prose, grouped by section, annotated with risk level and a 'why it matters' rationale. An agent can anticipate the result well enough to invoke the tool. Minor gap: the exact return structure/format isn't specified, but for a natural-language output tool this is a modest omission.

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 the schema already documents all four parameters (before, after, device, vendor). Per baseline rules, the description need not repeat param details. The vendor list lightly reinforces the 'vendor' parameter's accepted values, but adds no meaning beyond what the schema already conveys.

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 opens with a specific verb+resource: 'Explain what changed between two network device config snapshots, in plain English.' It is immediately distinguishable from all six sibling tools (cost estimation, VRAM checks, MCP auditing, etc.), none of which perform diff analysis. The vendor list further pins down the exact domain of applicability.

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 description gives clear applicability context by enumerating supported config formats (EdgeOS, MikroTik RouterOS, OPNsense, Cisco IOS-style, EdgeSwitch) and states the deterministic, offline behavior that would guide an agent's choice for privacy-sensitive or reproducible analysis. It does not explicitly name when-not-to-use or name an alternative tool, but no sibling is a plausible substitute, so exclusions are less critical.

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