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

Annotations declare readOnlyHint=true, and the description is consistent with a read-only metadata tool. It adds real behavioral value beyond the annotations by saying what each request returns (accounts yields workspace_id, brand_id, source metadata and available_actions; actions_details yields the exact request body, identifiers, fields, time ranges, notes). It does not state cost, rate limits, or response shape/size.

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 purpose sentence followed by clearly labeled steps, which is the right structure for a multi-mode meta-tool. The optional-call notes are slightly repetitive (available_actions is both a standalone call and included in accounts), but that redundancy is genuinely clarifying rather than wasteful.

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 five-parameter, four-mode discovery tool, the description supplies the workflow, the return contents of each mode, and the prerequisite ordering, while an output schema exists so return values need not be detailed. The one real gap is the undocumented `platform` parameter.

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 description coverage is 0%, so the description carries the burden, and it does explain the meaning of most values: the four enum values of `request`, the list form of `actions`, and the pairing of brand_id with workspace_id. The `platform` parameter is never mentioned anywhere, leaving one of five parameters completely unexplained.

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 states that this is a planning/discovery helper for Google Tag Manager queries, and the enumerated request modes (accounts, actions_details, available_actions, brands) make the resource concrete. It does not name sibling tools (query_data, execute_action) to distinguish itself explicitly, though 'REQUIRED before querying' implies the ordering.

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 an explicit numbered workflow: 'accounts' first, then 'actions_details' which is flagged 'REQUIRED before querying', plus which calls are optional. The condition for each mode is spelled out, so an agent knows the exact sequence and can tell when a mode is optional versus mandatory.

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