nvr_contact_sheet

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

With no annotations, the description carries the full burden and does well: it discloses the read-only intent, the side effect of writing frames into the export dir, the required environment (RTSP + ffmpeg), and the return shape (file info plus tile->timestamp map). It omits auth requirements, rate limits, and expected latency, which keeps it short of a 5.

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 core output is front-loaded in the first clause, and the remaining sentences each add a distinct fact (time format, side effect, return value, prerequisites). Dense but nearly every phrase earns its place, with only minor redundancy around the read-only/export-dir framing.

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 7-parameter tool with an output schema, no annotations, and 0% schema coverage, the description covers purpose, side effects, prerequisites, and return contents well enough to invoke correctly. The residual gap is the undocumented channel, width, and stream parameters, which the agent can only guess at.

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% across 7 parameters, so the description must compensate. It usefully specifies ISO-8601 with a required UTC offset for start/end and explains that cols x rows defines the sampling grid, but channel, width, and stream are left entirely undocumented in both the description and the 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?

States a specific verb and resource: produces one JPEG contact sheet of cols x rows frames evenly sampled across a replay window, with timestamps burned in. This clearly distinguishes it from nvr_snapshot (single image) and nvr_export_clip (video), but it never names those siblings, so the agent must infer the routing itself.

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 gives a prerequisite ('Needs RTSP enabled and ffmpeg available') and an implied use case (visual overview of a replay window), but it does not say when to prefer this over nvr_snapshot, nvr_sample_frames, or nvr_export_clip. Usage is implied rather than stated.

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