ask_garden

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

With no annotations, the description carries the behavioral disclosure burden. It does add useful traits: the operation is local, deterministic, and returns cited structured conclusions. However, it does not disclose whether the agent performs any writes, what sources it consults, or any limitations, which leaves gaps for a complex agent 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?

The description is a single, front-loaded sentence with no filler words. Every clause adds meaning: the operation, its mode, and its return format are all present.

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 output schema exists, return values are covered by structured data. However, the description is thin for a complex 'full cognitive retrospective Agent' with several similar siblings, and lacks any context about what the agent does with the question or how it relates to the other tools.

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 for documenting the 'question' parameter, but it does not. It provides no guidance on question format, scope, language, or what makes a well-formed input for this agent.

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 ('run') and resource ('full cognitive retrospective Agent'), and clarifies that it returns structured conclusions with citations. It does not explicitly differentiate from siblings, but the agent-based framing is distinct from the search/read/discovery tools listed.

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?

No guidance is given about when to use this tool versus the sibling tools such as discover_cognitive_shifts, search_sources, or get_topic_timeline. The phrase 'local deterministic path' hints at a specific mode of operation but not at selection criteria.

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