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

With no annotations, the description carries the full burden and does so well: it declares partial-update semantics ('Only what you give changes'), that instructions replacement is destructive ('replaces them'), and that changing provider resets the model. It stops short of describing error behavior or what the call returns, leaving a small gap for a mutation tool.

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?

Everything is packed into one front-loaded sentence that begins with the verb and resource, and each semicolon clause carries real information. The dense parenthetical style makes it slower to parse than it needs to be, but nothing is filler.

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?

For a six-parameter mutation tool with no annotations and no output schema, the definition covers mutation semantics, field-specific behavior, and permission guardrails thoroughly. It omits return/error expectations and does not flag the tool as destructive or confirm whether the change is reversible, which would be the last missing piece.

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 coverage is only 17%, so the description must compensate and mostly does: it explains instructions semantics, enumerates valid model values per provider, defines the provider enum plus its reset side effect, gives a folder format example and the '' sentinel for none, and points the required 'agent' param to list_agents. The 'name' parameter is left implicit, though its meaning is self-evident.

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?

States a specific verb and resource ('Change one of the user's Caddie agents') and enumerates exactly the fields it mutates (instructions, name, model, provider, folder). It also names the adjacent tools it is not (set_agent_access, organize_agents), so an agent can route correctly without opening a schema.

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?

Gives explicit when-not conditions: from an agent's own turn, instructions are never changed, nor the folder of an agent with Full access or Edits, nor a Full-access agent's provider/model — and directs the caller to 'ask the user' instead. It also routes by concern to set_agent_access for access and organize_agents for sections.

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