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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the safety profile is covered. The description usefully adds return-value context: ids plus minimum VRAM at 4-bit/8K context and system RAM for MoE expert offloading. It omits pagination/ordering behavior, which keeps it from a 5.

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?

One front-loaded sentence with the action first and the output content second; the parenthetical examples earn their place. Slightly dense but no wasted clauses.

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 4-parameter search tool with no output schema, the description is adequate on purpose and return content but leaves pagination (limit/offset) and the language-of-links parameter unexplained, and doesn't state result ordering. An agent can call it but may misuse the undocumented parameters.

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 only 50%: query and lang are documented in the schema, while limit and offset are bare. The description adds little beyond echoing 'by name' for query and says nothing about limit, offset, or the lang link-language parameter, so it does not compensate for the coverage gap.

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 ('Find') and resource ('open-weight LLM versions') with concrete model-family examples, and says what the result contains (ids, minimum VRAM at 4-bit/8K). It does not explicitly contrast with siblings like models_for_gpu or search_hardware, so it falls just short of a 5.

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 phrase 'by name' implies usage when the agent has a model-name query, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. models_for_gpu for reverse lookup). Guidance is only implicit.

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