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

Beyond the readOnlyHint/idempotentHint annotations it discloses the response shape ({data, pagination}) and a non-obvious operational caveat: the returned cursor is not read back on the next call yet, so paging forward requires narrowing since/until. That is genuinely useful behavioral context. It slightly restates the read-only safety profile, but the pagination limitation is the kind of detail annotations cannot carry.

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 sentences, none wasted: purpose and scope first, return/pagination caveat second, sibling routing third. Front-loaded and appropriately sized for a 7-param list tool.

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?

Output schema exists and the description still summarizes the return envelope, plus filtering and alternatives. The one friction point is that the description calls the cursor unusable for paging while the schema presents it as a normal pagination cursor, leaving the agent to reconcile the two.

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; the description still adds filtering semantics (check, state, time range) and the critical guidance that the cursor parameter cannot currently be used to page forward, which contradicts the schema's cursor text and is important for correct invocation.

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 (list internal incidents) with scope: organization-wide, active or resolved, filtered by check/state/time. It explicitly names the two sibling tools it is not (diagnose_check, get_status_page include=incidents), so an agent can route without inspecting schemas.

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 explicit alternatives with the condition that selects them: diagnose_check for one check's incidents plus current health, and get_status_page include=incidents for customer-facing entries. The read-only/mcp:read note also signals when the tool is unavailable or inappropriate.

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