create_agent

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals concrete side effects: it creates a multi-file bundle, optionally writes a provided persona or a fill-in template, and refuses to overwrite an existing agent. This goes well beyond the schema by stating the failure condition and pre-existing-agent behavior.

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 compact and front-loaded: starting with the core operation, then when to use it, then parameter specifics, then the failure guard. Every sentence adds actionable information and none merely repeats the schema. The structure makes it easy for an agent to scan and extract decision-critical facts quickly.

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 simple 3-parameter create tool with an output schema present, the description covers what is created, when to use it, how each optional parameter behaves, and the collision behavior. The output schema handles return-value details, so nothing essential to a correct first invocation is missing.

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 add meaning to parameters, and it does. It explains `name` as the display name, defaulting to `agent_id`, and `persona` as free-text identity for the AGENT.md body with an omit-for-template option. `agent_id` is not individually described, but its role is inferable from the required constraint and its use as the fallback for `name`.

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 opens with a precise verb and resource: 'Create a new agent bundle' and enumerates exactly what is created ('directory + AGENT.md persona + index.md + log.md'). This clearly differentiates it from sibling tools like delete_agent and the wiki_* operations. The 'Use when starting a new role' clause anchors the tool's specific purpose.

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 a clear trigger: 'Use when starting a new role that doesn't exist yet.' It also warns that the tool fails if the agent already exists and says 'don't clobber,' which implicitly tells the agent not to use it for existing roles. It does not explicitly name alternative tools for updates, but the usage context is unambiguous.

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