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

The annotations already declare readOnly, idempotent, and non-destructive behavior, so the description's extra context is valuable rather than redundant. It discloses the potentially large context cost, explains how pruning and depth collapsing behave, and notes that 'at' reads from mutation history — all beyond what annotations provide.

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?

Three sentences, front-loaded with the core purpose, followed by targeted parameter guidance and an optional timestamp explanation. Every sentence earns its place and there is no redundant restating of the schema or annotations.

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?

Given the annotations cover safety and idempotence, the schema covers parameter semantics at 100%, and an output schema exists, the description fully covers what an agent needs to invoke the tool correctly. It even includes edge-case behavior such as absent addresses being skipped.

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 input schema already covers all four parameters with clear descriptions, so the baseline is 3. The description adds meaningful behavioral context beyond the schema, particularly the warning that this is the biggest context cost on large models, the pruning/splicing behavior, and the mutation-history interpretation of 'at'. This raises it to 4.

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 states a specific verb ('Get'), a specific resource ('a model's merged state'), and clarifies it includes base fields plus computed derived fields. This clearly differentiates it from siblings like get_model_info, get_field, or get_view, which target narrower or different aspects.

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 description gives clear practical guidance on how to invoke the tool for large models: pass 'paths' to project subtrees and/or 'depth' to cap nesting, and pass 'at' for point-in-time reads. It does not explicitly name alternative tools or exclusion criteria, but the usage context is strong enough for an agent to decide when to use it.

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