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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint, destructiveHint=false, yet the description adds meaningful non-annotation context: the format of the output (plain-language meaning + step-by-step fix), that it is instant (latency), and that it uses no network.

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?

Three short sentences that each carry a distinct piece of load-bearing information – output format, usage trigger, parameter constraint – front-loaded and free of filler.

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 small, read-only lookup tool with rich annotations and a fully documented schema, nothing an agent needs to invoke it correctly is missing; the trigger conditions, input constraint, and output shape are all covered.

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%, but the description adds a critical semantic constraint the schema does not: rule_id must be passed exactly as returned by scan_app, i.e. it is a whitelist key, not arbitrary user input.

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 (returns plain-language meaning and step-by-step fix for one finding) and scopes it to a single entity, distinguishing it clearly from the sibling scan_app which produces findings rather than explaining them.

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 serialization behavior ('Pass the rule_id exactly as scan_app returned it') tells the agent which value to feed in, and the trigger conditions are named explicitly: while helping fix an issue from scan_app, or when the user asks what a finding means. No ambiguity remains.

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