aism_diagnostics

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real value beyond them: the required capabilities (diagnostics:read and manage_options), a companion version floor (1.6.0+), and a performance caveat that enabling site_health makes the call slower. It stops short of describing output volume or how log files are bounded, but the permission and cost disclosures are the substantive bits.

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 purpose, then a dense but scannable enumeration of included diagnostics, then the site_health caveat and prerequisites. Every clause carries information; the enumeration is long but each item is a distinct return field, not 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?

With no output schema, the description carries the burden of describing return content, and it does so thoroughly by listing every diagnostic category returned. Combined with the stated permissions and version requirement, an agent can decide whether this tool suffices. Minor gaps remain around output size/format and how log files are surfaced.

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 only 50%, with 'site' documented in-schema but 'site_health' left bare. The description compensates directly by explaining that site_health=true additionally runs the direct Site Health tests at the cost of speed, which is more useful than a terse schema line would be. The default-false behavior is left 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?

States a specific verb+resource ("Site overview") and then enumerates exactly what it aggregates: WP/PHP/DB versions and limits, constants, theme, plugins/MU plugins, drop-ins, object cache, cron summary, log files. This clearly distinguishes it as the aggregate diagnostic view versus the many narrow siblings like aism_cron_list, aism_plugins_list, aism_db_tables, and aism_logs.

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?

Frames the use case explicitly ("for troubleshooting") and gives a clear decision rule for the optional flag: site_health=true runs the direct Site Health tests and is slower. It does not name the narrow siblings it replaces (e.g. use aism_cron_list instead when you only want cron), so the routing guidance is strong but not exhaustive.

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