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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for going further: it discloses the two-stage mechanism (pre-gating at reject edges, then scoring on value/ratings/footprint/mount type) and a real output caveat that incomplete source specs can never yield a clean 'recommended'. It stops short of describing result volume or how ties/near-misses are surfaced.

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 front-loaded sentences that lead with purpose, then mechanism, then the caveat — a logical order with little waste. 'The ... cross-reference the Kelvin web app runs' is slightly ornamental and the packet is dense, but every clause contributes.

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?

For a six-parameter tool with zero schema descriptions, no output schema, and no enums, the description omits the required `family` argument and all filtering/limiting semantics. An agent knows the intent but not how to construct a correct call or what shape of result to expect.

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% across six parameters, so the description carries the full burden and fails: `family` is a required parameter that is never mentioned, and `same_type`, `max_results`, `manufacturer` and `target_manufacturers` are entirely unexplained. The listed dimensions (value, ratings, footprint, mount type) are scoring criteria, not inputs, so they do not compensate.

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: 'Find substitutes for a part by MPN', plus the distinctive framing that this is the deterministic, program-only path rather than an LLM-driven one. That implicitly separates it from recommend_parts, but the sibling is never named, so differentiation is inferred rather than explicit.

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 'deterministic, program-only ... No LLM judgement' phrasing implies when to pick this over a generative recommender, and the note about incomplete originals implies when results will be weak. However, no alternative tool is named and there are no explicit use/don't-use conditions for the sibling set.

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