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

Annotations only give the coarse aggregate (destructive=true, not idempotent, not read-only), and the description usefully refines that per action: list and status are read-only, create only saves a detached draft that no bot uses, and both stop/start require owner approval. It does not explain retry/idempotency semantics even though an idempotencyKey parameter exists, so the mutation-action behavior is not fully disclosed.

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 summary sentence, then a hard constraint, then per-action headers with required fields and purpose. The structure makes it scannable despite the length, and each section carries non-duplicated routing or requirement information.

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 4-action, 8-parameter tool with deeply nested objects and no output schema, it covers selection, exclusions, required fields, and even sketches the status response contents. The gaps are minor: preview/create responses and idempotency behavior for create are not described.

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%, so the baseline is 3, but the description adds genuine structure the schema only scatters: it groups required fields under each action and instructs 'Only send the fields listed for that action,' which prevents cross-action field mixing. It leaves the nested scheduleMetadata cadence variants entirely to the schema, which is acceptable given the coverage.

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 sentence names four specific operations (read/preview/save draft) on a specific resource and distinguishes the tool from start_deployment/update_deployment_revision by stating that a running bot's schedule can never be changed here. Each action section then defines its own verb+resource. An agent can tell exactly what this tool does and does not do.

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?

Explicitly states which sibling to use instead for each adjacent need: stop_deployment + start_deployment to reschedule, update_deployment_revision to change an existing bot schedule, start_deployment for initial schedules, and preview-before-start. It also states the exclusion up front ('a running bot's schedule can never be changed here'), which is exactly the when-not guidance an agent needs.

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