cleanup_account_temp_files

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

With no annotations supplied, the description carries the full behavioral burden, and it does disclose the deletion targets up front, which is genuinely useful. However, it never states that the operation is irreversible, that purging session caches may log out active users, or what permissions or scope limits apply — material facts for a destructive bulk cleanup tool.

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?

A single tightly written sentence that front-loads the benefit and follows with the concrete actions, with no filler or redundancy.

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 destructive, no-annotation, no-output-schema tool, the description covers what is removed but omits reversibility, session-logout side effects, and what a dry run reports back. It is adequate to pick the tool but incomplete to call it safely in production.

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 dry_run parameter is documented in the schema as reporting without deleting, so the schema does the semantic work. The description says nothing about dry_run, neither confirming nor adding to its meaning, so baseline 3 applies.

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 description gives a specific verb-and-outcome pair ('free up disk space') and enumerates exactly the three resources it touches: trash bins, error_log files, and temporary session caches. That distinguishes it clearly from siblings like delete_file, get_disk_usage, or get_error_log, so an agent can select it without opening the 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?

Usage is only implied by the phrase 'free up disk space' — there is no explicit when-to-use or when-not guidance, and no routing to alternatives such as get_disk_usage for diagnosis or delete_file for targeted removal. An agent can infer the intent, but must guess at prerequisites and edge cases.

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