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

Goes well beyond the readOnlyHint annotation by confirming the operation is free, never marks anything as read, and has specific pagination behavior. This is especially valuable for a notifications tool, where side effects like marking messages read would be a real concern.

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?

Four sentences, each earns its place: purpose, default behavior, pagination, and exclusions. The most important information is front-loaded and there is no filler or repetition of schema details.

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?

Despite having no output schema, the description sufficiently explains return shape (ten per group with cursors), pagination mechanics, side-effect guarantees, and access limitations. An agent has everything needed to invoke the tool correctly.

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?

The schema only describes an opaque cursor and category enum, but the description explains the default no-argument behavior, how category and cursor combine to page, and that each group returns cursors for further paging. This adds meaningful usage semantics beyond the schema.

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?

Description opens with a specific verb and resource ('Read your account messages') and enumerates exact content groups: support, billing, and account notices. It also states an exclusion (no security alerts), making the tool's scope unambiguous relative to siblings about phases, balance, and usage.

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 calling instructions: no arguments returns the ten most recent in each group, while passing a category and cursor pages further back. It also says when not to use it, noting security alerts aren't available and disabled groups won't appear.

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