manage_action

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

With no annotations, the description carries the full burden and does well: it discloses that UNASSIGN retains the action in the file, that NEW creates an empty action and assigns it, that ASSIGN shares one action across objects, and that PUSH_DOWN moves the active action into an NLA strip. It leaves out prerequisites (object mode/type, whether NEW clobbers an existing action or what happens when action_name is missing for ASSIGN).

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 one-line purpose is front-loaded, then Args/Returns structure the detail without padding. Every line adds semantics rather than restating the schema titles, though the Args block repeats parameter names already visible in 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?

A mutation tool with no annotations and a declared output schema; the description covers the operation semantics and the key side effects (retention on UNASSIGN, NLA conversion on PUSH_DOWN) that an agent needs before calling it. Remaining gaps are error/precondition behavior rather than core semantics.

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 compensate, and it does: object_name is identified as the animated object, action_name is scoped to NEW and ASSIGN (a conditional requirement the schema does not express, since the field is optional with an empty default), and the operation enum is fully glossed. It does not say what error or fallback occurs when action_name is omitted for the operations that need it.

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 opening sentence names the resource precisely ('an object's actions (its saved animations)') and the five operations enumerate exactly what the tool can do, so an agent knows it manages action datablocks rather than keyframes or NLA strips directly. It stops short of differentiating itself from adjacent siblings such as add_nla_strip or list_nla, which overlap with the PUSH_DOWN operation.

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?

Each enum value carries an inline explanation of what it does and the consequence ('UNASSIGN (stop playing the active action, keep it in the file)', 'several objects can share one'), which effectively tells the agent which operation to pick for which intent. It does not state when to use this tool versus the sibling NLA tools that perform similar layering.

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