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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered. The description adds useful context that two helpers are gated behind an enablement switch, but says nothing about what happens on invocation of a disabled helper (error vs empty result) or about rate limits across helpers.

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?

Two tight sentences, front-loaded with purpose and followed by the enablement caveat. The helper name list is slightly redundant with the enum but stays short and readable.

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 an openWorld dispatcher with a free-form nested params object, the description leaves the per-helper input contract mostly undocumented (only company_lookup is covered in the schema). Given no output schema, it also gives no hint of what discovery results look like, so the agent is under-informed for several helpers.

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 75%, so the schema already documents params, vanity (for company lookup), platform, and account_id. The description's enumeration of helper values restates the enum rather than adding semantics, and it does not explain the free-form params object beyond the single company_lookup case.

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 ('Run a platform helper') and resource ('account-specific discovery'), then enumerates the concrete helper names. An agent can distinguish it from most siblings, though it does not clarify its relationship to overlapping tools like get_x_posting_quota or list_analytics.

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?

Implies this is the route for account-scoped platform data and notes that company lookup and YouTube playlists require being switched on first, which is a genuine prerequisite. However, it never says when NOT to use it or points to sibling alternatives that cover overlapping functionality.

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