provenance

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

Annotations already state readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description adds context those don't convey: the value is inferred so it is stamped `basis: git-history` and 'never raises' a trust tier, which tells the agent this mutation is safe-but-low-confidence. It doesn't say a git repository is required or what happens when history is absent.

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 action and tightly packed—nearly every clause adds information about derivation source or safety semantics. Density comes at the cost of readability, but there's little pure filler.

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 3-param write tool with no output schema and 0% schema coverage, the description explains semantics and the dry-run path but omits `bundle`, does not identify which files it edits, and never states the git-repo prerequisite.

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%, so the description must carry the load: it does define `skip` ('paths to leave without it') and `apply` (dry-run vs write). The third parameter, `bundle`, is never mentioned anywhere in the description or schema, leaving a real 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?

Opens with a specific verb+resource: fill a missing `generated: {by, at}` field, and explicitly scopes it to concepts that lack that field ('Concepts that carry `generated` are left alone'). An agent can tell it apart from mutators like `set` or `fix`, though it never names a sibling directly and leans heavily on spec jargon (§5.2, 'AI trailer', 'verified').

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?

Gives the triggering condition (missing `generated`), an exclusion (already-populated concepts are untouched), and a preview path ('apply=False shows the diff'). It stops short of naming alternative tools for related repair tasks, so the agent must infer the boundary with `set`/`verify`/`fix`.

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