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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the three list variants return identical catalogues, so calling more than one is redundant. It says nothing about pagination, default result size, or sort order despite having limit/offset and a score field.

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, front-loaded with the action, followed by the de-duplication rule and the selection criterion. No filler and no repetition of the title or annotations.

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?

The sibling-disambiguation problem, the hardest part of this tool family, is fully solved, and there is no output schema to explain. However, an eight-parameter unannotated-in-schema list tool should at least describe pagination defaults and what the remaining filters accept; an agent can pick the tool but will likely guess at parameter usage.

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 0% – all eight parameters carry only titles and defaults, with no explanation of format. The description adds meaning only for the scope-related filter and payload ("semiconductor-layer scope and payload"), leaving pays, categorie, min_score, limit, offset and the in_scope_only=true default entirely unexplained. With zero coverage the description needed to carry far more of this burden.

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 ("List the robot catalogue with filters") and immediately scopes it to semiconductor-layer and payload filtering. It explicitly distinguishes itself from the near-identical siblings mechanical_list_robots and software_list_robots, which is the key disambiguation an agent needs here.

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?

"Returns the same catalogue as the mechanical and software variants - call one, not three" plus "Pick this one to filter on whether a robot is in scope for the semiconductor layer" gives an explicit selection rule against the three parallel list tools. It gives no guidance relative to the other hardware_* siblings such as hardware_get_robot or hardware_compare_robots, so the routing is strong but not exhaustive.

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