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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the default filtering mode hides non-actionable findings, so an agent knows its view is already curated unless it passes detail="all". It omits what happens when audit_id is unknown or the check is still running, which keeps it from a 5.

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?

One sentence with the return payload front-loaded and the enum semantics appended in a parenthetical; every clause carries information. The nested quoting inside the parenthetical makes it slightly harder to parse than a two-sentence split would be.

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, so the description must characterize the return value, and it does enumerate the fields delivered (state, summary, counts, findings). For a simple two-parameter read tool with full schema coverage and annotations, the only missing piece is failure behavior for a stale or invalid audit id.

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%, so the baseline is 3, but the description goes further by defining the two enum values semantically — "actions" yields issues and warnings only, "all" yields every finding — which the schema only labels as "Default \"actions\"" without explaining the distinction.

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?

Specific verb and resource: "Returns the compact report of an earlier check," followed by the concrete payload (state, summary, counts, findings). It is clearly a result-retrieval tool distinct from run_checks (which produces audits) and list_checks (which enumerates them), though it never names those siblings explicitly.

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?

"of an earlier check" implies the prerequisite that an audit must already exist, and the schema reinforces this via audit_id "returned by run_checks." But there is no explicit when-to-use vs when-not guidance, and no routing between this and list_checks or verify_fixes for an agent deciding which report view to fetch.

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