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

Beyond the destructiveHint/openWorldHint annotations, it discloses precisely which commands need approval (uninstall/delete, DB drops or resets, new keys, admin login link, tinker/php:eval), the interaction behavior per toolchain (--no-interaction for Symfony/artisan, -y required for drush), and the background-execution trait. This is substantive behavioral context the annotations cannot express.

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 dense paragraph that front-loads the core action before branching into per-CMS binaries, approval rules and flags. Every sentence carries information, but the parenthetical CMS list and flag details make it heavier than it needs to be for a first read.

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 high-variance, multi-framework shell-execution tool with no output schema, the description covers the critical unknowns: which binary runs, Docker behavior, approval gating, non-interactive flags and long-running handling. Nothing an agent needs to invoke it correctly 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?

The schema documents site, server, why and approval_id, but leaves args and background bare; the description compensates with concrete examples (["cache:clear"], ["plugin:list", "--json"]) and states that background should be true for slow commands. That adds real meaning over the 67%-covered schema, though it doesn't cover every edge (e.g. arg quoting/escaping rules).

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 names a specific verb and resource ('Run a site's own command line tool as the site's owner, in the site's folder') and enumerates the exact binary per CMS (bin/console, artisan, drush, cli/joomla.php, ghost), which separates it from siblings like magento, wp, run and db_query. An agent can identify the tool without opening any 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?

It routes the agent explicitly to alternatives ('Magento 2 has the magento tool and WordPress the wp tool'), tells the agent to consult list_sites for each site's console, and gives clear conditions for approval-required commands versus ones that run straight away. The Docker case ('runs inside the container') is a concrete usage condition rather than a generic statement.

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