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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real substance beyond them: the 90-day aggregate window vs. by-id reads at any age, the reason_code vs. status_message distinction, and that action_data is the step configuration as it was at run time. The deduction is for internal inconsistency — it says retry "is refused here" yet later tells the agent to "and retry to re-run a failed or paused run" with its params, which no `action` enum value supports.

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 read-only framing and action list, and the dense single paragraph still follows a usable diagnostic order. It loses a point for the retry sentence, which adds length and confusion about an action the schema forbids.

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?

With no output schema, the description carries return-shape duty and mostly delivers: health's totals/failure rate/blockers, get's ordered step trail, error, retry counts and action_data. What's missing is any sense of list result shape or pagination envelope, and the retry passage muddies which actions are actually callable.

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 100% and every parameter already carries an action-scoped description, so the schema does most of the work; the description's per-action param listings ("params: since, until", "params: type [required], id [required]") restate that mapping. It adds margin insight into when to filter by reason_code or contact_id, but little param meaning beyond the schema.

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?

Opens with a specific verb and resource plus an explicit non-effect ("Read executions — this tool changes nothing") and enumerates the three actions (health, list, get). It also names the sibling that owns writes ("Anything that writes (retry) is on `executions_manage`"), so an agent can distinguish this from `executions_manage` without opening either 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?

Gives an explicit ordered diagnostic playbook (health → scenarios/campaigns `performance` → list → get) with the condition that selects each step, plus concrete branching advice such as filtering by reason_code and calling health first for codes actually occurring. It also states what an empty list-by-contact_id result means, which steers the agent to a different tool.

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