compare_model

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

With no annotations provided, the description carries the full behavioral disclosure burden. It clearly says the operation is a structural comparison and lists the compared elements, and 'compare' implies a read-only operation. However, it does not explicitly state that models are not modified, nor does it describe what happens when one of the given model IDs is not open or invalid.

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?

The description is a single well-focused sentence that front-loads the verb and resource, then uses a colon to list the comparison categories. Every element adds information, with no filler or repetition of the schema.

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?

The comparison categories are enumerated, which gives a strong hint about the expected output content. However, with no output schema and no annotations, the actual return format is unspecified — an agent cannot know whether the result is a structured diff object, a list of changes, or a summary. Given the low parameter count, the description is usable but not fully complete.

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 schema provides only parameter names and titles with 0% description coverage, so the description must compensate. It maps the two parameters to 'two open models', indicating that model_id_a and model_id_b are model identifiers and that the models must already be open. It does not explain how to obtain these IDs (e.g., via list_open_models) or the expected ID format, leaving some ambiguity.

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?

The description specifies a clear verb ('compare') and resource ('two open models'), then enumerates exactly what is compared: added/removed/modified tables, columns per table, references, and domains. This level of specificity distinguishes it from siblings like inspect_schema or get_model_info, which focus on a single model rather than a diff between two.

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 'two open models' implies the use case — use this when you need to diff the structure of two models. However, there is no explicit guidance on when not to use it or which sibling (e.g., model_snapshot, inspect_schema) might be a better alternative for single-model inspection. Usage is implied, not stated.

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