create

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

Annotations already declare a non-readonly, non-destructive, non-idempotent, closed-world write, so the bar is lower. The description still adds genuine traits beyond them: refusal on existing files (so no upsert), refusal of reserved names (index.md, log.md), an automatic `# title` heading unless the body already opens with one, and a `generated {by, at}` block injected when `by` is supplied.

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?

Front-loaded with the core action, then field enumeration, then behavioral caveats. Dense but every clause carries information; the '§4.1' spec reference is the one piece that adds little for an agent without the document.

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 10-parameter mutation with no output schema and no per-parameter schema documentation, the description covers the frontmatter contract well but leaves gaps: `bundle` is entirely unaddressed, `file` path handling is unstated, and nothing indicates what is returned (path, content, or confirmation) so the agent cannot plan follow-up calls.

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% across 10 parameters, so the description must carry the load, and it does for most: type, title, description, resource, tags, status, body, and by are all given meaning in the frontmatter model. Two parameters remain opaque — `bundle` is never mentioned and `file` (path semantics, relation to bundle) is only implied by the refusal clause.

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 concept with valid OKF frontmatter (§4.1)'. That distinguishes it from sibling mutations like set, rename, archive, or ingest. The only weakness is domain jargon ('concept', 'OKF'), which an agent unfamiliar with the bundle model must infer.

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 rather than stated: 'Refuses an existing file or a reserved name' tells the agent this is create-only and cannot overwrite, which implicitly routes updates to siblings like set or fix, but no alternative is named. There is no explicit when-to-use/when-not guidance and no prerequisites (bundle initialization, required type values).

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