add_always_include

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

No annotations are provided, so the description carries the behavioral burden. It discloses the effect ('automatically included in every task pack'), which explains the consequence of adding a ref. However, it doesn't reveal whether the operation is additive/merge, idempotent, reversible, or what happens if the ref already exists. It also doesn't state auth or permission requirements.

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?

Three sentences, front-loaded with the core action and the key behavioral consequence. The typical-use line adds value without bloat. No wasted words, though the structure could arguably place the typical-use line first for quicker skimming.

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?

The description explains core purpose and consequence, but for a governance-affecting mutation tool with no annotations, it's somewhat thin. It doesn't address edge cases (duplicate refs, invalid refs) or clarify whether the change is immediately effective or requires reindexing. An output schema exists, which relieves the return-format burden, but the absence of behavioral depth keeps this from being fully complete.

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%, but there is only one parameter (ref) and its meaning is reasonably inferable from the tool purpose. The description does not add syntax, format, or validation details for ref beyond the schema's type:string, so it doesn't add substantial value over the schema. With a single well-named param and 0% coverage, a baseline of 3 is fair.

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 clearly states the verb (add) and resource (a ref to the always_include list), and explains what the list does ('Any ref in this list is automatically included in every task pack'). It distinguishes this from siblings like add_external_ref and add_governance by naming the specific destination list, though it doesn't explicitly differentiate from the sibling tools.

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 a clear typical use case ('a personal-prefs governance entity you want everywhere'), which signals when to use it. However, it doesn't mention when NOT to use it or name alternatives (remove_always_include for removal, add_governance/add_external_ref for other ref types), leaving the when-not guidance implicit.

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