aism_maintenance

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

Annotations already declare a non-read-only, non-destructive, non-idempotent, open-world mutate tool; the description adds value beyond them by disclosing that recurring events are rescheduled after run_cron, that rewrite flushing is a soft flush, and that maintenance:write plus manage_options are required (companion 1.6.0+). It does not describe outcomes or failure modes for the flush/delete actions.

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-loaded with the umbrella purpose, then one compact clause per action; nothing is repeated from the schema verbatim. The parenthetical asides make it dense but every clause carries operational information, so it stays readable in a single pass.

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 four-action mutation tool with no output schema, it covers permissions, host caveats, and side effects (rescheduling), which is the information an agent most needs before invoking. What is missing is any indication of what each action returns or what happens on partial failure.

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 80%, so 3 is the floor; the description still adds meaning by explaining that key disambiguates multiple argument sets for the same hook and that hook/key originate from aism_cron_list, which the schema alone does not convey. Timestamp and site semantics are left entirely to 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?

Each of the four enum actions is given a concrete verb+resource: run_cron fires a scheduled event now, flush_cache empties the object cache, flush_rewrite_rules regenerates permalinks, delete_expired_transients removes expired transients. It also routes the agent to aism_cron_list as the source of hook/key, so the boundary with that sibling is clear.

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 gives a real selection condition — run_cron 'works on hosts without working WP-Cron' — plus the conditional 'pass key when the hook has several argument sets'. It does not, however, say when flush_cache vs flush_rewrite_rules would be appropriate, nor any when-not-to-use exclusions.

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