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

Beyond the annotations it discloses what actually gets destroyed (temporary search state only, not user files), which materially softens the destructiveHint=true flag for an agent deciding whether to call it. It also adds non-obvious operational context the annotations cannot carry: account-bound computer:write OAuth plus possible prompted local owner approval.

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?

Three short sentences, each doing distinct work: what it does, what it does not destroy, the alternative tool, and the auth prerequisites. The primary action is front-loaded with 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?

For a single-parameter session-teardown tool with no output schema, the description covers action, non-effects, sibling alternative, and authorization requirements. Nothing an agent needs before invoking it is missing.

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% and the schema already explains the id is from the corresponding start/list operation and is not a device PIN. The description adds only the redundant phrase "by ID" and no further format or sourcing detail, so this is the expected baseline.

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?

"Discard an EXZA search session by ID" gives a specific verb (discard), a specific resource (search session), and the keying parameter. The clause "freeing only temporary search state; does not delete user files" scopes it precisely against the file-mutating siblings like exza_trash_home_file or exza_edit_commander_file.

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 explicitly routes the agent to exza_get_commander_search_results when the goal is to read results, which is the main ambiguity for a stop tool. It does not state the positive trigger (e.g., call after results are consumed or to release session resources), so the when-to-use side is only implied.

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