Manage Media Watch

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

With annotations that only declare non-read-only, non-idempotent, and non-destructive behavior, the description adds meaningful safety-relevant detail: it records only bounded file-change signals, is session-scoped, and never imports media automatically. This helps an agent predict side effects better than the annotations alone. It could still state more about what happens to existing monitor state on repeated start calls, but the added context is solid.

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?

Two tight sentences capture the resource, operations, scope, behavioral bounds, and key exclusion (no automatic imports). Every phrase earns its place and the primary operations are front-loaded.

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 description covers the monitor lifecycle and its safety profile, and an output schema exists so return values do not need to be described. It is complete enough for an agent to understand the tool's role, though it does not spell out prerequisites like whether watch_path must be inside approved_workspace_path. That detail is left to the parameter schemas.

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 all parameters. The description adds minimal parameter-level meaning, mostly by mapping "rescan" to the scan action and framing the monitor as non-importing. This meets the baseline but does not go beyond it with additional insight such as flags, defaults, or path restrictions.

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 names a specific resource (one session-scoped local media-folder monitor) and a precise set of operations (start, inspect, rescan, stop). It also explicitly distinguishes itself from import tools by stating it "never imports media automatically." This clearly separates it from siblings like preview_watched_media_import and import_media.

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 conveys the intended use context: managing a local media-folder monitor rather than importing media. It does not explicitly name an alternative tool or state "use X instead," though the "never imports media automatically" line rules out using this tool for imports. The lifecycle verbs also make the available actions reasonably discoverable.

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