observe

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

No annotations are provided, so the description carries the full burden. It discloses the key behavioral traits: it does not advance the simulation and does not consume the step budget, and it enumerates the exact return fields with units. It does not cover error conditions or permissions, but for a non-mutating observation tool this is largely adequate.

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?

It is a single dense sentence but front-loads purpose before listing returns; every clause provides useful information. It could be slightly more scannable, but there is no filler or repetition.

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 no output schema and no annotations, the description fully documents the return shape (two labeled PNG images, state fields with units, step counters, status) and the side-effect profile, leaving no significant gap for an agent invoking this zero-parameter read tool.

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?

The tool takes zero parameters, so the baseline is 4. There are no parameters to clarify and the description appropriately focuses on outputs instead.

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 (Read) and resource (current RGB images and end-effector/gripper state) and adds the crucial scope constraint 'without advancing the simulation or using the step budget,' which sharply distinguishes it from the actuation siblings like move_relative and set_gripper.

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 'without advancing the simulation' clause implies when to use it (inspection without stepping), but it never names an alternative or says when not to use it. Sibling get_session_info is not mentioned as a differentiating option.

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