mc_observe

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

No annotations, so the description carries the full burden and does so: it discloses the render semantics (players humanoid, hostile monsters red / passive yellow, dropped items black-outlined, dark purple = unloaded chunk), the conflict-resolution rule (program raycast wins over client prediction), and an explicit uncertainty section warning against treating guesses as fact. It also notes the inline delivery and the gate mode opt-in via view.json.

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 purpose and usage, which is good, but the body is dense with emoji bolding and includes tangents — the gate-mode config file path and the mc_kit_express save workflow are peripheral to invoking this tool. The core message survives, but a fair amount of the text could be cut without loss.

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?

No output schema and nine optional parameters, yet the description explains what comes back (inline image plus three-part perception, with an option to suppress either via `image`/`percept`) and where files land. Combined with 100% schema coverage on the tuning knobs, an agent has enough to call it correctly; only token/size trade-offs are hinted rather than spelled out.

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%, with ranges and defaults already documented for fov, width, height, distance, image, percept, entities and crosshair, so the baseline is 3. The description only adds meaning for `out` (route to .express/<subdir>/ and fetch via mc_kit_express, default lands in .out/), leaving the other eight parameters entirely to 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: render a first-person screenshot from the player's eyes and return it inline with a three-part perception breakdown. It also names what the perception contains (pixel ratios, entity positions, crosshair target, held item, program raycast, nearby entities with coords/health), so the agent knows exactly what it gets back.

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?

Explicit both ways: read-only queries (mc_status / mc_inventory / mc_scan) don't need it, but 'look once before acting' for dig/place/break/build, moving, finding things, confirming entities, or when stuck. It also gives a cadence rule (one image per action segment, re-look when the environment changes), which is unusually actionable.

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