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

Annotations declare readOnlyHint=false and destructiveHint=true, and while the description's 'Refresh' is consistent with a mutation, it never explains why the operation is destructive — whether prior analysis is overwritten, what is lost, or that re-analysis consumes resources. It adds domain context about the analysis contents but nothing about mutation side effects.

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 the action and resource, followed immediately by the usage condition. No filler or redundancy.

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?

No output schema exists, but the description is not expected to explain return values. The main gap is behavioral: for a tool flagged destructive with a force parameter, the description never says what gets overwritten or what 'force' guards against doing to existing state, leaving a meaningful ambiguity.

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 all three parameters (force, agentId, customerId) are already documented in the schema. The description adds no parameter-level meaning beyond that, making the baseline 3 appropriate.

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 (Refresh) and resource (structural analysis of an agent's system prompt), with a parenthetical that enumerates what the analysis contains (strengths, weaknesses, opportunities, quality metrics). This differentiates it reasonably from adjacent tools like refresh_agent_insights or analyze_agent, 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?

Explicitly states the triggering condition: 'when the agent's prompt has changed or you need to re-evaluate its structure.' Clear context for invocation. However, it names no alternative tool and gives no when-not guidance (e.g., versus analyze_agent or refresh_agent_insights).

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