preflight_change

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

With no annotations, the description carries the full behavioral burden and handles it well: it states 'Read-only; nothing is applied', which is the decisive safety trait, and it also discloses the conditional blast-radius behavior and the exact verdict vocabulary. No annotation contradiction exists.

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 dense sentences front-load the operational context ('Before you push a change') and then enumerate the analysis steps, verdict, and safety property. Every clause earns its place; there is no filler or repetition of schema boilerplate.

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?

For a preflight gate with an output schema, the description is nearly complete: it names the verdicts, covers the core diff inputs, defines blast-radius conditions, and states read-only status. The remaining gaps are minor but real: device/vendor parameters are unexplained, and no sibling routing is given for diff-only or compliance-only needs.

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?

The description adds meaning for current/proposed (the diff pair) and fleet (configs of other managed devices for blast radius). However, schema description coverage is 0% and the description never mentions the 'device' or 'vendor' parameters, leaving those roles to be guessed despite the vendor options in the schema.

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 verb and resource: diff a proposed config against current, risk-tag changes, identify compliance regressions, and compute blast radius, ending in a gate verdict. The 'gate verdict' framing clearly separates it from sibling tools like explain_config_diff and check_config_compliance, which only analyze or check rather than gate a change.

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?

'Before you push a change' gives an explicit trigger condition, and the 'if you pass the configs of the other devices you manage' clause defines when fleet input matters. It does not name alternatives or explicitly say when NOT to use this tool, so it falls one step short of the top score.

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