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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds meaningful behavior: a sensor fault is reported and does NOT stop the lease, and the lease-state requirement. It omits timeout/rate behavior, keeping 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?

Three short sentences, with the read-only safety signal and the core resource front-loaded, followed by the precondition and edge case. No wasted text.

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?

There is no output schema, and the description still explains the return form (an image, or the latest reading of a named feed) plus the failure mode. That is everything an agent needs 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 100%, so both parameters are already documented. The description adds only marginal meaning for `feed` (that it returns the latest reading of another offered feed) and nothing about lease_id beyond the schema's 'Lease id.' Baseline 3 applies.

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?

Names a specific verb (read/get) and resource (latest frame from the leased robot's camera feed), and covers the alternate case of a named feed. An agent can distinguish it from get_robot_status or list_robot_commands without opening the schema.

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?

States the precondition that the lease must be ACTIVE and supervisory, which tells the agent when the call is valid. It does not name a sibling alternative for cases where no frame is available, but the context is clear.

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