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

Annotations are minimal (readOnlyHint false, destructiveHint false, etc.), so the description carries responsibility. It discloses the costly behavior of start_workflow ('spends the account's credits unattended') and that cooldown is the only bound, plus persistence ('survives the conversation'). It also states authentication, account tier, and scope requirements. These go beyond the annotations and give the agent a realistic expectation of side effects.

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?

The description is three sentences with zero fluff. The core purpose is front-loaded in the first sentence, followed by the key benefit and persistence trait, then a necessary cost warning. Every sentence adds value; there is no redundant phrasing or repetition of schema property names.

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?

The tool is complex (8 parameters, nested action_config, 5 required) and has no output schema, so the description needs to cover the overall behavior and important context. It explains the trigger logic, persistence, costs, and prerequisites. It does not mention the return value (e.g., a monitor ID), but since there is no output schema, the description is not required to; still, a brief hint about the returned object would make it fully complete. Given the strong schema coverage and sibling presence, a 4 is appropriate.

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 100%, so the schema already documents every parameter. The description adds a conceptual mapping ('a count you name' → subject, 'a line you set' → threshold, 'do the thing you chose' → action) but does not add syntactic details or edge-case notes beyond the schema. With full schema coverage, a score of 3 is the appropriate baseline; the description adds marginal clarifying context.

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 a specific verb and resource: 'Save a standing watch' which is the monitor, and explains its function clearly ('fires later, on its own: when a count you name crosses a line you set'). It distinguishes from siblings like list_monitors and delete_monitor by focusing on creation and persistence across conversations. The purpose is unambiguous and does not restate the tool name.

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?

The description provides clear context for when to use the tool: to 'bank a condition and stop polling for it', implying this replaces manual polling. It also notes the watch 'survives the conversation', so it's for long-lived checks. It does not explicitly name alternative tools or give when-not-to-use conditions, but the contrast with polling and the distinct lifecycle make the usage clear enough.

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