model_reference

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

With no annotations at all, the description carries the full behavioral burden. To its credit it discloses the return payload in both modes (index lines vs. full description, parameters and a copied example), which substitutes for a missing output schema. It says nothing about behavior on an unrecognized topic name, whether the lists are exhaustive, or that the call is purely a static read with no side effects.

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?

It is a single sentence that front-loads the core definition and then branches cleanly into the no-topic and with-topic cases. The long parenthetical value lists make it dense and slightly hard to scan, but every clause carries actionable information.

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 one-optional-parameter lookup tool with no annotations and no output schema, the description explains both call modes and what comes back, which is the bulk of what an agent needs. The remaining gaps are edge behavior: invalid topic strings and whether a bare call is expensive enough to avoid repeating.

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?

The single 'topic' parameter has 0% schema description coverage, so the description must compensate, and it does: it enumerates concrete op names (extrude, hole, plane, split, mate, constrain, text, feature, helix, pattern, weld, shell) and topic categories (sketch, faces, arcs, planes, assemblies, workflow). The enumeration is explicitly non-exhaustive ('such as'), leaving some ambiguity about whether an unlisted string works.

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?

It states precisely what the resource is (the 3D modelling reference) and defines both operating modes: no topic returns a one-line index of every op and topic, while a topic returns the full description, parameters and a worked example. An agent can distinguish this lookup tool from siblings like model_describe or model_query without opening the schema.

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 two modes imply when to call each (browse first, then drill into a named op/topic), which is reasonable usage guidance. But there is no explicit when-not guidance and no mention of the closely related siblings (model_describe, model_query, model_build), so the agent must infer that this is documentation rather than live model interrogation.

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