ignore

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

Annotations are empty, so the description carries the full burden. It discloses genuinely non-obvious behavior — gitignore matching semantics and 'Ignored numbers are still never reused' — which an agent could not infer. It omits permission requirements, error behavior, and whether removing a non-existent pattern fails, leaving meaningful gaps for a mutation tool.

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?

Purpose is front-loaded, followed by matching semantics, then the dry_run hint and the never-reused note. The pattern-syntax enumeration is dense but each clause carries needed meaning; no filler sentences. Slightly compressed but efficient.

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?

With no output schema and no annotations, the description must stand alone. It covers pattern semantics, dry_run, and a key invariant, which is solid for a config tool, but says nothing about available collections, error handling, or result shape when previewing.

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 only 25% (only `collection` is documented), so the description must compensate, and it largely does: it explains the pattern syntax that applies to `add`/`remove` entries (`#`, `!`, `/` anchoring, trailing `/`, depth rules) and the role of `dry_run`. Only `collection` is left to the schema.

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 description opens with a specific verb pair and resource: 'Add or remove a collection's `ignore:` patterns', immediately clarified as 'numbered files that are not initiatives'. This is clear despite the vague tool name `ignore`. It does not explicitly distinguish itself from siblings like `create`/`update`/`tidy`, but the domain scoping is precise enough for an agent to place it.

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?

'Use dry_run to preview which files a change would ignore' is the only usage guidance and it targets dry_run rather than when to reach for this tool over `update` or `tidy`. Usage context is implied by the domain but no alternatives or exclusions are named.

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