create_thought

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It discloses a key side effect: 'Thoughts are automatically enriched with AI classification, categorization, entity extraction, and embeddings in the background.' This adds useful context about asynchronous processing. However, it does not mention return values, permissions, failure modes, or reversibility, leaving notable gaps for a create operation.

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 two sentences with no fluff. The first sentence front-loads the core purpose and content types; the second adds the required condition and a valuable behavioral note. Every word earns its place.

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 creation tool with no output schema and no annotations, the description covers the essential context: what it creates, required inputs, and background enrichment. The schema handles parameter details. However, it omits information about what the tool returns or how errors are handled, which would be useful for an agent invoking it.

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 100%, so each parameter is already well-documented (e.g., max lengths, stream precedence). The description adds one critical cross-parameter constraint: 'At least one content type is required', which is not enforced by the schema but is essential for valid usage. This goes beyond the individual parameter descriptions.

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 clearly identifies the tool's verb ('Capture') and resource ('a new thought'), and specifies the three content types (text, images, links). This distinguishes it from sibling tools like get_thought, list_thoughts, and search_thoughts, which are all read operations. The purpose is unambiguous and specific.

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 states an important usage condition: 'At least one content type is required', guiding the agent on necessary input. It also implies this is the tool for creating thoughts, distinct from the read-only siblings. However, it does not explicitly name alternative tools or state when not to use it, so a full exclusion is missing.

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