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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the description's job is context — and it adds real value: default scope is *open* advisories, results are severity-ordered, and each row carries an actively-exploited flag. It does not clarify what 'open' excludes (dismissed/resolved) or pagination behavior, which is the remaining gap.

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, front-loaded with scope and ordering, and the final sentence earns its place by describing return content absent from any output schema. Slightly dense in the middle clause where five filters are compressed into one list.

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 6-param read tool with annotations and no output schema, the description covers scope, ordering, filtering, and a key return field (exploited status). The main omission is the advisory lifecycle model — with dismiss/resolve/acknowledge siblings present, an agent needs to know what 'open' excludes.

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% and every filter is documented in-schema, including defaults and enum values, so the baseline of 3 applies. The description's enumeration of severity/category/site/source/acknowledged largely restates the schema, though pairing 'acknowledged' with the open-advisory framing adds modest interpretation.

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 and resource ('Open advisories for the agency') plus default scoping (open only) and ordering (severity-first), which is far more than the tautological title 'List alerts'. It does not explicitly name the sibling it differs from (fleet__get_advisory, fleet__security_triage), so sibling differentiation is left implicit.

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 filter list implies when this list view is appropriate, but the description never says when to use it versus fleet__get_advisory (single advisory), fleet__security_triage, or the lifecycle siblings acknowledge/dismiss/resolve_advisory. No prerequisites or exclusions are given.

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