start_draft_monitor

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

Annotations (readOnlyHint=false, destructiveHint=false) say little, so the description carries the burden and delivers: it discloses the monitor waits while paused or stale/incomplete, clears obsolete cached results, appends calculation evidence including discarded batches, and explicitly states 'This tool neither reads a browser nor submits picks.' This is valuable behavioral context beyond the sparse annotations, though it could mention what happens on repeated invocation when a monitor already exists.

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 core action, then prerequisites, then behavior, then alternatives. Each sentence earns its place and the flow is logical. Slightly long for a background-starter, but every clause adds routing or behavioral value, so nothing is wasted.

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 an output schema present, return values need no explanation. The description covers prerequisites, behavioral quirks (stale/paused/incomplete waits, cache clearing), non-interaction guarantees, and alternative tools. Nothing an agent needs to decide whether to call this tool and how to set it up is missing.

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 both parameters are already documented. The description adds behavioral nuance by explaining each batch uses the latest imported snapshot and that batch duration adds to the interval, but it doesn't significantly extend meaning beyond the schema's own parameter descriptions. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource: 'Start background draft simulations and return the initial monitor status.' This clearly distinguishes the tool from siblings such as recommend_draft (synchronous single calculation) and get_draft_recommendations (results retrieval). The description makes the tool's role unambiguous without needing to inspect schemas.

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 prerequisites ('Requires a loaded draft snapshot and no active local draft monitor') and names exact alternatives with their conditions ('Use get_draft_recommendations for results, stop_draft_monitor to stop, or recommend_draft for one synchronous calculation'). This is textbook routing guidance – an agent knows precisely when to invoke this tool versus its siblings.

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