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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the safety profile is largely covered; the description adds the important behavioral facts that account-wide scope is limited to 'only the candidates this user can see' and that the write is time-bounded by `receivedBefore`. It does not state whether the change can be undone, what permissions are required, or what the call returns, which keeps it out of the top band for a mutation tool with no output schema.

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, zero filler, with scope breadth stated before the temporal qualifier. Every clause adds information an agent needs to choose parameters correctly.

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?

For a 3-parameter, all-optional tool whose default is account-wide, the description covers scope resolution and the time bound, which are the primary risks of mis-calling. It leaves out reversibility and the response shape, but with annotations covering mutability/idempotency and no output schema, those gaps are minor.

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 individual parameter text already carries the baseline. The description still adds combination semantics the schema documents only piecewise: that `candidateIds` needs no position and that omitting everything resolves to the whole account, plus the effect of `receivedBefore` (later replies remain unread).

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 ('mark candidate email replies as read') and immediately enumerates the three distinct scoping modes: explicit candidates, one job position, or whole account. An agent can tell this apart from the sibling read-side tool (list_unread_messages) without opening either 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?

Gives concrete contexts for each scope ('for specific candidates (`candidateIds`, no position needed), for one job position, or for the whole account') and explains exactly how `receivedBefore` narrows the operation so later replies stay unread. It never names the complementary sibling (list_unread_messages) as the alternative for reading rather than mutating, so the routing guidance is clear but not exhaustive.

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