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

With no annotations, the description carries the full behavioral burden and does add real value: it discloses that the model is free and open-weight, and quantifies latency at roughly five words per second, which lets an agent judge timeouts. It does not say what the response looks like, whether errors surface as text or exceptions, or whether there are rate limits — gaps that matter since no output schema exists.

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, zero padding. The latency caveat is placed inline where it is most useful, and the invocation pattern is front-loaded at the end where an agent needs it before calling.

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 three-parameter text-generation tool this is close to sufficient: it covers what the tool is, how slow it is, and how to compose the arguments. The one missing piece is the return shape, which the absent output schema leaves entirely to the description.

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 the baseline would be 3, but the sentence 'Give q, or task plus text' adds a genuine composition rule the schema lacks: the schema marks nothing required and never says that q is mutually exclusive with the task/text pair. That single clause materially reduces misuse.

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: querying WezzetAI, an open-weight language model, with a named identity. It is clearly distinguishable from siblings like calc, check, or read_url, which do deterministic or retrieval work. It stops short of 5 because the description doesn't frame the tool as 'free-form text generation' relative to any comparable alternative.

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?

'Fine for drafts, summaries and quick questions' gives implied usage guidance, and 'slow: about 5 words a second' signals when to avoid it for latency-sensitive work. There are no explicit when-not-conditions and no named alternatives among the siblings, so the agent must infer the boundaries.

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