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

readOnlyHint=true is consistent with the described behavior, and the description goes beyond annotations by disclosing what each call returns (workspace_id, brand_id, available_actions, exact request body, required identifiers, fields, time ranges, notes). The mandatory actions_details gate is a genuine behavioral constraint an agent must honor. Missing auth/permission requirements and any rate-limit or error behavior keep it from a 5.

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 in one line, then organized as Step 1 / Step 2 / Optional, matching the intended call sequence. The placeholder 'xxxxxx' values usefully demonstrate the expected argument format. Slight redundancy in restating that available_actions is already covered by accounts, and two trailing 'Optional' blocks dilute the priority ordering.

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?

Five parameters at 0% schema coverage, but the description compensates by documenting the enum-driven workflow and the arguments for each mode. An output schema exists, so the limited return-value narrative is sufficient. An agent has enough to plan and execute the setup sequence without guessing.

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?

With 0% schema description coverage, the description carries the load and largely succeeds: it explains all four 'request' enum values, gives the shape of 'actions' with a literal example, and pairs brand_id with workspace_id for the 'brands' call. The 'platform' parameter is never mentioned anywhere, which is the one real gap.

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 opening line states the tool's role concretely: a planning/metadata helper for CallRail data queries, not a data fetcher. Each request value ('accounts', 'actions_details', 'available_actions', 'brands') is described with the specific resource it returns. It does not name the siblings (execute_action, query_data, prompts_menu) explicitly, so the boundary with those tools is inferred from 'before querying' rather than stated.

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?

'Step 1' / 'Step 2' sequencing plus the 'REQUIRED before querying' directive tells the agent exactly the order in which to call this tool and how it gates downstream calls. It also discriminates between overlapping options: available_actions is marked optional and explicitly noted as 'already included in accounts response', which is a real when-not rule.

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