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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false), and the description reinforces it with the familiar 'as opening it in the dashboard does' analogy, which usefully communicates the effect and its low risk. However, it never mentions the required confirm flag for hard-to-undo actions or whether the operation is reversible, leaving a behavioral gap.

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?

One sentence, front-loaded with the action and scope, with zero filler. The dashboard analogy is compact and adds meaning 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 simple two-parameter write tool with full schema coverage and no output schema, the description is nearly sufficient. The only missing element an agent might want is a nod to the confirmation guard, though that is discoverable from the schema.

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 100%, so both enrollment_id and confirm are already documented in the schema (including the 'hard to undo' confirmation semantics). The description adds nothing about parameters, so the baseline 3 applies.

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 ('mark ... as read') and resource ('every unread message in an inbox thread'), including the scope of the mutation. It does not explicitly contrast itself with the sibling get_thread or list_inbox_threads, so an agent must infer the read-vs-fetch distinction from the verb alone.

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?

Usage is implied rather than stated: the dashboard analogy signals 'use when you want the thread to look opened.' No when-not condition or named alternative (e.g., get_thread for reading without mutating) is provided.

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