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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely new behavior: authorization is required per-robot, the operation is all-or-nothing, and a refusal names the offending robot and compares nothing. That atomic-failure semantic is exactly the kind of thing annotations cannot convey.

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?

Two sentences, no filler. The capability statement is front-loaded and the precondition/failure mode follows, which is the right order for an agent deciding whether to call.

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 exists, and the description compensates by naming the compared dimensions, so the agent knows roughly what comes back. The precondition and failure behavior are covered; the only material omission is the input format for multiple robot IDs.

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% and robot_ids is an undescribed string, so the description carries the burden. It contributes the cardinality bound (2 to 5), but never specifies the encoding of multiple IDs in a single string parameter (comma-separated? array-like?), leaving a real ambiguity for the caller.

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 (compare), a bounded resource set (2 to 5 robots), and enumerates the exact comparison dimensions: software BOM, TCO, jurisdiction exposure, lock-in, export control risk. The 'software' domain plus those dimensions distinguish it cleanly from hardware_compare_robots and mechanical_compare_robots without needing to name them.

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?

Gives a clear triggering condition (side-by-side comparison of 2-5 robots in the software domain) and a hard prerequisite (access right on every listed robot). It does not explicitly route the agent to the hardware/mechanical siblings when the domain differs, so the exclusion is implied by the title rather than stated.

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