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

Annotations only declare readOnlyHint=true, so the description carries the real load: it enumerates the status state machine (pending/delivered/failed/expired), expands the pending sub-stages, and discloses billing and recovery behavior (not charged on failure, can resend, render_failed requires the person to reopen the link). That is behavior an agent cannot get from the annotation.

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?

The critical instruction and the accepted identifier forms are front-loaded, and the state definitions are dense but each earns its place. The parentheticals make it slightly longer than needed, but there is no filler.

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?

There is no output schema, yet the description documents the returned fields (status, stage, pages, price) and their meanings, which is exactly what the agent needs to interpret the response. Nothing material is missing for a single-parameter read tool.

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% for the single id parameter, so the baseline is 3. The description restates the id-or-address duality and adds the 'status address from the tracking prompt' phrasing, but adds little semantic weight 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?

The opening sentence 'Read where a fax is' gives a specific verb (read) and resource (fax status), and the surrounding detail about id vs. address forms makes the scope unambiguous. It is clearly distinguishable from siblings create_fax and list_supported_formats.

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?

It states the trigger condition ('read the status when the person asks') and an explicit when-not ('Do not call this in a loop'), and points to create_fax as the source of the id. It stops short of naming an alternative tool for status reads, but no such sibling exists.

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