lint_vault

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

With no annotations provided, the description carries the full burden and does substantial work: it discloses the two result classes (errors vs warnings), their subcategories, and the contents of stats.tags. It never explicitly states that the operation is read-only and makes no changes to the vault, which is the main remaining gap for a mutation-adjacent concept.

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 structured into errors, warnings, and stats.tags. The long parenthetical enumerations are information-dense rather than repetitive, though they could be tightened slightly.

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?

There is no output schema, yet the description explains the return shape (errors, warnings with their causes, stats.tags census fields) thoroughly enough that an agent knows what to expect. For a parameterless lint tool, nothing essential 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline applies. No misleading parameter language is present.

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 statement ('Lint all vault files against the Loci schema') and then enumerates exactly what it detects (schema violations, unknown types, bad/duplicate uids, dangling relations, duplicate tags). This is clearly distinguishable from a single-node validator like validate_type or check_duplicate.

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?

Explicitly states when to run it: 'after manual vault edits or when debugging unexpected behavior.' That gives a concrete trigger. It does not name an alternative or say when not to use it (e.g., versus validate_type for a single node), so it stops short of a 5.

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