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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the stream contains deploys, config changes and comments, which is genuinely useful content beyond annotations, but it says nothing about volume, default lookback behavior, or whether tag filtering narrows server-side. With annotations carrying the safety burden, this is an adequate but not rich disclosure.

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, no filler, with the positive identification front-loaded and the sibling exclusion as a compact second clause. Every sentence 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?

All parameters are optional and an output schema exists, so the description does not need to explain return values or required inputs. For a 7-parameter tool it holds up reasonably, though an agent would still lack guidance on default lookback (hours=1) or result-count expectations if it does not read the schema closely.

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 71%, so most parameters self-document; the description's only parameter-relevant contribution is the phrase "in a time window," which hints at the start/end/hours relationship already spelled out in the schema. It adds nothing about `tags` filter syntax, `priority` values, `limit` truncation, or the `context_id` workspace override. Baseline 3 is appropriate where the schema does most of the work.

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?

Names a specific verb and resource ("List Datadog events") and enumerates the concrete event classes (deploys, config changes, comments), which maps directly to what an agent would expect from an events stream. It also explicitly distinguishes itself from two sibling tools, so the agent can route without opening any schema.

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?

"Not a substitute for dd_logs_search or alerts_active" gives clear negative routing guidance, and "in a time window" implies the use case is time-bounded event history lookup. It stops short of a positive statement of when this tool should be preferred (e.g., correlating a deploy with an incident window), so it is clear context but not full when/when-not coverage.

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