delete_rtsps_stream

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

No annotations are present, so the description carries the full burden. It discloses key behaviors: case-insensitive normalization, no local allow-list with the upstream API governing unrecognized names, and channel availability caveats (package only on doorbells). It does not explicitly state irreversibility or permissions, but 'delete' implies destructive action. The added edge-case warnings go beyond a minimal description.

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 moderately lengthy but every sentence delivers essential detail. The primary action is front-loaded, followed by parameter-specific clarifications. There is no fluff or repetition, though the parameter block could be slightly more compact without losing 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 delete operation with three parameters, the description covers all inputs, legitimate values, and a practical source for camera_id. It does not describe success/failure responses or state that the action is irreversible, but an output schema exists to define return values, and the destructive nature is implied by the tool's name. Overall, sufficient for an agent to invoke it correctly.

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 0%, so the description must fully compensate. It does: host formats are listed (console name, ID, composite ID), qualities includes the exhaustive set, explicitly excludes 'highest', explains case-insensitivity and forwarding behavior, and marks camera_id as required with a source instruction. Every parameter receives thorough, actionable meaning beyond the bare 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?

The description opens with a specific verb and resource: 'Delete an RTSPS stream for a Protect camera.' This clearly distinguishes it from siblings like get_rtsps_stream and create_rtsps_stream. The scope is well-defined and no ambiguity remains about what action is performed.

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 implicitly clarifies when to use the tool via the verb 'Delete' and provides concrete guidance such as sourcing camera_id from list_cameras. It does not explicitly name alternatives or state 'use this when you want to delete,' but the context is clear enough for an agent to select it correctly among many siblings.

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