mark_unread

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the safety profile is covered structurally. The description only adds the single-message scope, saying nothing about permission requirements, behavior on an already-unread message, or failure modes; with annotations present a 3 is fair but the added value is thin.

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 short lines with the action front-loaded and no wasted prose. The "Args:" block is a minor formatting artifact rather than padding.

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 three-parameter mutation tool with no output schema, the definition covers the action and the parameter provenance but omits return behavior, error cases, and the meaning of the account/mailbox params. It is workable but leaves real gaps for an agent to guess at.

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%, so all three parameters (account, mailbox, id) carry no field-level documentation. The description partially compensates by saying the values come from search_messages, which is genuinely useful, but it never explains what account or mailbox mean or accept, leaving two of three params ambiguous.

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?

The description opens with a specific verb and resource ("Mark a single message as unread") and scopes it to one message, which lets an agent distinguish it from a plural/bulk sibling. It never names mark_read or any alternative, so sibling differentiation is only implicit.

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?

The only usage cue is that the args are "As returned by search_messages", which implies a search-then-mark workflow. There is no statement of when to prefer this over mark_read or how it behaves on threads/collections, so guidance is implied rather than explicit.

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