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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true; the description doesn't explain why marking as read is destructive or what effect it has on the notification record. It does add useful context: an explicit confirmed=true gate before execution and that the ChannelOAuthId header is resolved internally, which is genuine value beyond the annotations.

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?

Padded with meta-commentary ("This is an explicit tool with a fixed endpoint; it is not a generic endpoint caller"), a redundant "Search terms:" line, and repeated purpose statements. The one operationally important fact (confirmed=true required) is buried mid-paragraph rather than front-loaded.

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 needn't be explained, and the confirmation gate plus header resolution are covered. But for a destructive mutation with three sibling variants, the description leaves the agent unable to tell which mark-as-read tool to pick or what specifically is destroyed/changed.

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 body, confirmed and channelOAuthId are all documented in the schema itself. The description only names "rq: MarkAsReadRequest" and repeats the confirmed requirement, adding no field-level semantics or payload shape guidance beyond what the schema provides.

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 the verb and resource ("POST mark as read operation in notification centre operations") and names the endpoint, but the phrasing is template boilerplate ("Provides the X operation") and never distinguishes it from the near-identical siblings hgr_post_notificationcenter_markallasread and hgr_post_notificationcenter_markallchannelasread, which is exactly the ambiguity an agent needs resolved.

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?

"Use when: Use it when a client needs to run the mark as read operation" restates the name instead of giving a condition. No alternatives are named despite three mark-as-read siblings in the tool list, and no prerequisite beyond the confirmed flag is given.

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