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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation profile is known. The description confirms it is a write ('returns the newly written snapshot') but never explains what the destructive refresh overwrites, whether previously generated sections are lost, or whether the operation is idempotent/reversible. It also omits that the customerId path requires superadmin rights (that detail exists only in the schema), so it adds limited context beyond the annotations.

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 tight sentences with zero filler: the action and its return are front-loaded, followed immediately by the triggering conditions. Every clause earns its place.

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, and the description compensates by stating that the newly written snapshot is returned, and the parameter surface is fully documented in the schema. The remaining gap is behavioral: for a destructive refresh the agent is not told what is overwritten or whether recomputation is expensive, which is the one thing 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 100%, so the baseline is 3 and the schema already documents all three parameters including the superadmin caveat, the timeFilter enum, and the effect of regenerateFullInsights. The description adds only the vague notion of a 'fleet-level report' and does not clarify parameter trade-offs or defaults.

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 gives a specific verb+resource pair ('Force-refreshes persisted fleet intelligence') and states the return ('the newly written snapshot'), which is far from a tautology. It implies fleet-level scope versus the agent-level 'refresh_agent_analysis'/'refresh_agent_insights' siblings, but never names or explicitly contrasts with them, so differentiation is inferred rather than stated.

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?

It specifies two concrete trigger conditions: 'get_fleet_intelligence reports stale or missing trend confidence' and 'a recent ingestion needs the fleet-level report recomputed immediately', explicitly naming the read counterpart the agent should check first. That is a clear when-to-use plus the alternative, with nothing left to inference.

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