Create goal

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 discloses id assignment, filename derivation from the H1, that a validation failure returns a non-raising ValidateResult and writes nothing, and that only frontmatter (not the body) is returned. The remaining shortfall is the heavy embedding of internal ADR UUIDs and issue numbers (ADR f14f125e..., ADR 519d1206, issue #204, feat-110) that are not actionable for the calling agent.

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 operative behavior is front-loaded in the first sentence, but the second sentence is a dense run-on of implementation trivia—ADR UUIDs, GitHub issue numbers, 'case 5 of the ADR 519d1206 non-raising-structured-result workaround chain'—that costs the reader without helping tool selection. Much of this should be dropped or tightened.

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, so return-value explanation is optional, yet the description usefully notes frontmatter-only return and the follow-up get_gol call. The mutation path (nothing written on validation failure) is covered, leaving only parameter-format detail as a minor gap.

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% for the single `content` parameter, so the description must compensate. It partially does by clarifying this is body-only content and that the H1 title drives the filename, but it never names the parameter explicitly or states format constraints (e.g. markdown vs plain text), leaving a gap.

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 first clause states a specific verb (Create) and resource (goal), and the surrounding detail (assigns id, derives filename, validates body, writes to goal base directory) makes it unmistakably distinct from siblings like get_gol, list_gol, and parse_gol. An agent can identify the operation without inspecting the 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?

Usage is implied (create a new goal document) and it routes the agent to get_gol for the full document afterward. However, there is no explicit when-to-use guidance relative to the other create_* tools, nor any stated preconditions such as required permissions or where the base directory lives.

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