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

Annotations only cover safety (readOnlyHint, openWorldHint). The description goes well beyond that, disclosing that results are ranked by the provider's own test scores, returned best-first, that supplying hardware+memory switches to a fit-only filter, and that each result carries the quantization to download and its memory requirement. This is material behavioral context an agent cannot infer from annotations.

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?

Front-loaded with the usage trigger, then return behavior, then three concrete examples that map user utterances to arguments. No sentence is redundant and the example list earns its length by disambiguating intent.

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 describing what comes back (ranking order, fitted models, quantization, memory needed). For a read-only, parameter-light lookup tool this covers everything an agent needs to call 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 baseline is 3, but the description adds real meaning: it explains the hardware/memory_gb coupling ('with a GPU or Mac memory size it only returns models that fit') and maps natural-language intents to the sort_by dimensions and max_params_b via its examples. It does not clarify the limit cap of 30.

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 the best models') plus the exact domain (local/open-weight LLMs, coding/documents/decisions, VRAM-fittable). It separates itself from get_model and compare_models by framing itself as a ranked recommendation lookup, though it never names a sibling explicitly.

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?

'Use this whenever the user asks which local or open-weight LLM is best...' gives an explicit trigger condition with several qualifying scenarios and sample queries. It lacks explicit exclusions or pointers to compare_models/decision_models when the user wants a head-to-head rather than a single ranking.

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