model_info

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious context the annotations don't carry: bounds are 'unrotated' (so rotation is not baked in) and expressed in Source units. It omits error behavior for an unknown model, keeping 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 zero filler; the key qualifiers ('unrotated', 'Source units') appear before the purpose clause.

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 an output schema present, return values needn't be described, and the description does characterize them. But for a tool taking one required identifier whose schema is undocumented, the missing definition of 'model' is a real gap an agent could stumble on.

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 description coverage is 0%, so the description must explain the single required 'model' parameter — but it only hints via the token 'MDL'. It never says whether the argument is a file path, model name, or search key, leaving the agent to guess.

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?

Specific verb + resource: 'Read unrotated MDL hull bounds and dimensions' tells the agent exactly what comes back, and 'in Source units for accurate prop placement' pins down the intended domain. It is clearly distinct from siblings like search_models or list_dupes, though it never names 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?

'For accurate prop placement' implies the use case (sizing/positioning props in a build) but gives no explicit when-to-use/when-not and never points at an alternative for related queries such as search_models.

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