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

Annotations already declare a safe, idempotent, non-destructive read, so the safety profile is covered. The description adds real workflow context beyond them: that reading this list has no approval effect and that a separate evaluation call gates any use of the wording. It does not discuss the retired-filter behavior, though that is largely schema-visible.

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, front-loaded with what it reads, then the critical misuse warning, then the required follow-up call. No 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?

An output schema exists, so return values need not be described, and annotations cover safety. The workflow guardrail is present. The only gap is the unexplained parameters, particularly the required boardId and the includeRetired default.

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 0%, so the description must carry parameter meaning. Naming 'timelines and workarounds' loosely maps to the kind enum (TIMELINE/WORKAROUND), but boardId and includeRetired get no explanation at all, leaving the semantic burden essentially unmet.

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: reads/lists approved timelines and workarounds. It is clear what the tool returns, but it does not name or contrast itself with the nearest siblings such as list_approved_causes or list_statement_limits, so an agent must still infer which list applies.

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?

Gives a clear precondition and next action: call evaluate_customer_update with the exact wording before saying a promise. It also clarifies a common misuse (listing does not approve a different promise). It stops short of stating when not to use it versus the other list_* tools.

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