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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful behavioral context the annotations cannot: the result is evidence and not permission, and a missing state must not be fabricated — a real guardrail for an LLM consumer.

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?

Four short sentences, front-loaded with what is returned, then the evidence-not-permission caveat, then the required next call. Every sentence earns its place with 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-value explanation is unnecessary, and the description fully covers scope and the downstream sequencing constraint. The only gap is parameter meaning for boardId and limit, which neither schema nor description addresses.

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% across three parameters, so the description must carry the load. It only implies the 'question' parameter ('for a customer question') and says nothing about boardId or what 'limit' controls (default 8, max 20) — the selection cap on returned states is left unexplained.

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 ('Retrieve') and enumerates exactly what comes back: incident states for a customer question plus approved causes, timelines, workarounds, and statement limits. An agent can distinguish this composite evidence-fetch from siblings like search_incident_states or list_approved_causes.

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 downstream condition — call evaluate_customer_update before stating wording, a cause, a timeline, or a workaround — which names the alternative sibling and the trigger for using it. It stops short of explaining when to prefer this over list_approved_causes or search_incident_states directly.

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