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

Annotations already establish readOnly, idempotent and closed-world, and the description is consistent with all three. It adds genuine behavioral context beyond them: the three-way verdict taxonomy, the fact that each check and next steps are returned, and the conservative fallback that anything off the published list is reported as 'review', never 'supported'. That safety-relevant bias is exactly the kind of trait annotations cannot express.

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, front-loaded with the action and closing with the most decision-relevant behavior (the conservative 'review' fallback). The long parenthetical of matrix factors is dense but each item earns its place by telling the caller what is evaluated; it is slightly list-like inside prose rather than a bulleted structure.

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 nine parameters and no output schema, the description carries the return-value burden and does it: verdict, per-check results, and next steps are all named. It also explains the unknown-input behavior. It stops short of describing what 'next steps' contain or what the caller needs before invoking, leaving a small gap.

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 100%, so the schema already documents all nine parameters including enums, defaults and the uname -r format. The description names the matrix axes that correspond to those parameters (Linux 5.8+, InfiniBand/RoCE v2/NVLink, NCCL/RCCL) but adds no input syntax or value semantics the schema lacks. Baseline 3 is appropriate.

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 ('Checks') and resource ('a GPU cluster against XportL's published support matrix'), then enumerates the exact dimensions checked (kernel, fabrics, GPU vendors, collective libs, deployment, host access). None of the siblings (analyze_nccl_benchmark, calculate_fabric_degradation_cost, get_xportl_overview) overlaps this function, so an agent can route to it unambiguously.

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 description defines the evaluation surface but never says when to reach for this tool versus get_xportl_overview or request_enterprise_demo, nor what prerequisite inputs the caller must already have. Usage is implied by the verb 'Checks a cluster' — a pre-onboarding fit assessment — but the agent must infer the positioning itself.

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