Create decision

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 richly: filename derivation from H1, body-only validation, a non-raising ValidateResult (valid=False, errors[].message capped at 300 chars) on failure, and the crucial fact that nothing is written in that case. That failure semantics disclosure is exactly what an agent needs.

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 core action is front-loaded, but the text is padded with internal metadata -- ADR GUIDs, feat-110, GitHub issue #204, 'case 5 of the ADR 519d1206 chain' -- that adds no value for tool selection or invocation. Structure is a single dense run-on, which harms readability.

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?

An output schema exists, yet the description still usefully states the return is frontmatter-only (no body) and points to get_dec for the full document, plus covers failure behavior. For a single-param creation tool, nothing an agent needs to invoke it correctly 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 coverage is 0% and the single 'content' param has no schema description, so the description must compensate -- and it does by clarifying the input is 'body-only content' (not frontmatter), with the H1 title used for the filename. It adds real meaning, though it doesn't specify format/length constraints.

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 ('Create a new decision') and then enumerates the concrete internal steps: assigns id, derives filename from the H1 title, validates body-only content, writes to the decision base directory. This clearly separates it from the get_dec/list_dec/parse_dec siblings.

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?

It only gives one routing instruction -- use get_dec afterward to fetch the full document -- which is a follow-up pointer rather than explicit when-to-use vs alternatives guidance. There is no stated condition for choosing create_dec over, say, edit/update, nor any prerequisite guidance.

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