trigger_platform_helper

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds essentially nothing beyond duplicating the enum: it does not say whether helpers hit the live platform API, whether they can fail per-platform, or whether results are cached or rate-limited — relevant given openWorldHint=true.

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 short sentences, front-loaded, with no filler. However, the second sentence is a pure restatement of the helper enum and would be better spent describing what the helpers return or how to choose one.

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?

This is a gateway tool that fans out to six different helpers with an untyped free-form params object and no output schema, so the description carries a heavy burden. It fails to describe any helper's inputs, outputs, or failure modes, leaving the agent unable to use most helpers correctly from the definition alone.

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%, and the description merely re-lists helper names that already appear in the helper enum without explaining what any of them do or require. The one genuinely non-obvious parameter detail (linkedin.company_lookup needs {vanity}) comes from the schema's params description, not from the tool description, so no compensating meaning is added.

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 verb phrase 'Run account-specific platform helper discovery' is vague on its own, but the enumerated helper names (linkedin.company_lookup, x.quota, youtube.playlists) give a concrete sense that this dispatches to platform-specific lookup operations. It is distinguishable from siblings, though many siblings also read platform data and the description never says what a helper actually returns.

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?

There is no guidance on when to pick this tool over siblings such as get_x_posting_quota or list_google_business_locations, nor on when a given helper is appropriate. No prerequisites, no exclusions, no mention of how account_id vs platform selection should be decided beyond what the schema already states.

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