list_states

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile needs no restating. The description earns credit by disclosing the output contract (flat list with parent/child/sibling fields and a child_count that is explicitly recursive rather than per-level), which is genuinely useful behavioral information. It stops short of stating edge cases such as empty trees or invalid tree_path handling.

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?

Two sentences: the first front-loads the action and scope, the second compactly specifies the return shape. Tight and waste-free. The literal return-shape string is dense but justified by the absence of an output 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?

With no output schema, the description correctly carries the return-value burden and does so explicitly, and with only two fully documented read-only parameters and rich annotations, little else is required. The remaining gap is disambiguation from list_state_trees and get_state_tree_info, which an agent must resolve on its own.

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 100%, so both tree_path and root_state are already documented, including the non-obvious detail that top-level SubTrees are skipped when root_state is set. That places the baseline at 3. The description adds no additional parameter meaning beyond echoing 'UStateTree' and hinting at the root_state behavior through 'Walk the state hierarchy'.

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 pairs a specific verb (walk/list) with a specific resource (the state hierarchy of a UStateTree) and enumerates the returned relationships (parent/child/sibling, recursive child_count). It is clearly distinguishable in substance from list_state_trees, which lists trees rather than states. It does not, however, name any sibling, so an agent must infer the boundary from the resource noun alone.

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?

There is no statement of when to use this versus list_state_trees or get_state_tree_info, no prerequisites, and no exclusions. The only guidance ('If set, walk from this state as root') lives in the schema, not the description. An agent gets no routing help from the prose itself.

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