pending_changes

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

Annotations only grant readOnlyHint=true, but the description adds substantial behavior: what constitutes lockout risk (disabled pass rule / enabled block rule over the management path), worst-first ranking, the `certain` flag semantics, and what blocks vs warns. It also clarifies that `basis` reports staged STATE, not a diff — a non-obvious behavioral detail no structured field carries.

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-loads the [READ] tag, then usage, then behavioral detail, then args — a sensible ordering. Every section adds information, though the prose is denser than strictly necessary; the `basis` paragraph earns its place by preventing a state/diff misread.

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 and a single optional param, the description still describes what is returned (ranked findings, certain flag, basis semantics) and the gating relationship to apply_changes. Nothing needed to call it 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 description coverage is 0%, so the description must carry the param, and it does: 'target: Firewall target name from config; omit for the default.' This explains both the meaning and default behavior. It stops short of format examples, but for a single optional string it is adequate.

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: it reads the staged rule set that apply_changes would commit, specifically surfacing lockout risk. It is clearly distinguished from apply_changes (which commits) and from state-inspection siblings, and the [READ] tag disambiguates intent.

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?

Explicit routing: 'Run this BEFORE apply_changes,' which directly names the sibling it gates. It also describes the consequence of each finding class (certain ones make apply_changes refuse, uncertain ones warn only), giving the agent a clear decision model for when this tool matters.

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