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

The annotations already cover safety (readOnlyHint true, idempotent, non-destructive), so the description's job is supplemental context, which it supplies: a privacy caution about names and an explicit auth requirement ('account-bound computer:write OAuth and any prompted local owner approval'). It does not describe the shape or ordering of the returned list, which keeps it below 5.

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 short sentences, front-loaded with what is returned and what is not done, followed by the privacy note and the routing alternative. Slight awkwardness in 'with an approved recycleId only if needed' keeps it from being maximally tight, 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?

The tool has no parameters, no output schema, and full annotation coverage, so the description needs only to state the result vocabulary, the non-destructive posture, the auth prerequisite, and the follow-up tool; it does all four. The only missing detail is any hint about how many entries are returned or whether the list is ordered.

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?

This tool takes no parameters and the schema coverage is complete, so there is nothing for the description to clarify about inputs. The description correctly spends its words on the output vocabulary (names and recycle IDs) rather than inventing parameter behavior, which matches the baseline expectation.

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 specific verb (read) is combined with the exact resource (recycle-bin names and recycle IDs), and the phrase 'without restoring contents' distinguishes it from exza_restore_home_file and from the plain listing siblings such as exza_list_home_files. The agent can tell exactly what this tool returns without opening a schema.

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 description names the alternative tool (exza_restore_home_file) and the condition that gates it ('with an approved recycleId only if needed'), so the basic when-to-use path is clear. It stops short of stating when not to use this tool, but for a zero-parameter listing tool the routing guidance is adequate and helpful.

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