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

Goes well beyond the annotations: page size (25 at a time), sort order (newest first), the returned fields (sender, receiving number, read state), and an authentication requirement ("Needs the person to sign in to Faxette") that annotations cannot express. The non-mutating clarification reinforces readOnlyHint rather than contradicting it.

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?

Front-loads the triggering condition, then return shape, then parameters, then the read-only and auth caveats. Each sentence carries distinct information with no filler, and the pharmacy/today examples are short enough to earn their space.

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?

With an output schema covering return values, three fully documented parameters, and rich annotations, the description fills the remaining gaps an agent needs: paging behavior, ordering, auth requirement, and the fact that nothing is marked read. Nothing material is missing for correct invocation.

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 the baseline is 3; the description still adds the pagination loop semantics by telling the agent to feed next_page back as page, which clarifies how the two calls compose. The unread explanation largely restates the schema, and organization selection guidance lives only in 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?

States a specific verb and scoped resource: listing faxes the organization *received*, which separates it from get_faxes, get_fax, and get_inbound_fax without needing to name them. The opening clause ties the tool directly to a user-intent phrasing ("whether a pharmacy faxed back or what came in today"), so an agent can route to it confidently.

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 an explicit when-to-use condition plus concrete example scenarios, and explains the optional filter ("Pass unread to see only unread ones"). It also implicitly excludes opening/reading a fax ("It doesn't open or mark anything"), though it never names read_inbound_fax or get_inbound_fax as the alternative for that case.

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