gripper_grasp

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

Adds real behavior beyond the annotations: the exact success predicate (fingers must settle inside the epsilon band, reported as ok=true) and the important non-obvious rule that over-max forces are rejected rather than clamped, which changes how a caller should retry. Annotations already flag destructive/non-idempotent/openWorld, so the remaining gap is the failure aftermath (is the gripper left closed on failure? is an error raised?).

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?

Three tight sentences with zero filler; the action and its arguments come first, followed by the success criterion and the force-policy edge case in descending order of importance.

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?

An output schema exists so the ok=true return needs no further explanation, and annotations already carry the destructive/non-idempotent safety profile. What the agent actually needs to call this correctly — required width and force semantics, tolerance behavior, force rejection policy — is all present.

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 100%, so baseline is 3, but the description still earns a step: it explains how width_m and the two epsilon parameters combine into the acceptance interval, and clarifies that exceeding the force bound is a hard rejection (the schema only says 'must not exceed the policy maximum'). speed_mps is not mentioned at all in the description.

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 concrete verb and resource ('Close the gripper on an object') plus the two governing quantities (width_m, force_n), and adds the success predicate, so the tool's intent is unmistakable. It never names or contrasts with the nearby gripper_move / gripper_home siblings, so an agent must infer the split (grasp-with-force vs. positional move vs. homing).

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?

Usage is only implied: the success-band condition conveys 'use this when you know the object width and want a force-limited grasp', but there is no explicit when-to-use, no exclusions, and no pointer to gripper_move for plain positional commands or gripper_home for reset. The agent has to reason about the sibling family on its own.

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