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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the payload shape, including that a ready-to-run three.js loader snippet with clip playback is included, which is non-obvious behavior an agent can plan around.

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 sentence, front-loaded with the lookup key, followed by the return contents. Nothing is padded and no sentence is wasted.

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?

With no output schema, the description usefully covers what is returned, which is the main gap it had to fill. It falls short only on the optional pack parameter and on relating itself to the sibling discovery tools.

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% and the schema itself explains that 'name' should match what search_models returns. The description only gestures at 'by name' and says nothing about the optional pack disambiguator, so it stays at the baseline rather than adding meaning.

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?

Names the resource and key precisely: 'One model by name', and then enumerates exactly what comes back (.glb URL, clip names, pack, licence, three.js snippet). The singular 'one model' contrasts adequately with search_models and list_packs without needing to name them.

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?

Usage is implied rather than stated: an exact-name lookup, with search_models presumably used to discover names first. There is no explicit when-to-use/when-not or alternative named, so the agent must infer the routing from the singular phrasing.

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