vault_pack

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

With no annotations, the description carries the full burden and does substantial work: it discloses a token budget, that results are ranked and provenance-annotated, and what each result is annotated with (why matched, grounded-by, constraints, applicability). It stops short of stating it is strictly read-only, what happens when nothing matches, or any result-size guarantees beyond the budget framing.

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 what the tool is, then what it returns, then when to use it. Dense but every clause carries information; minor jargon ("provenance-annotated", "what constrains it") costs a little clarity without bloat.

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 annotations and no output schema, the description is the sole carrier of behavior and it adequately explains the return shape and the raison d'être (cheaper than reading whole notes). Gaps remain around the undocumented k and full_body parameters and any failure/empty-result behavior, but nothing essential to calling it correctly is absent.

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 only 40%, so the description needs to compensate and only partly does: "Budgeted" maps to budget_tokens and "grounded" maps to grounded_only, but k and full_body are never addressed in prose. Baseline 3 is appropriate given the schema's partial coverage and the description's partial fill of the 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?

The description names a specific resource (a budgeted, provenance-annotated context pack for a task or question) and states what it returns: ranked notes annotated with match reasons, grounding, constraints, and applicability. It implicitly separates itself from siblings like vault_search and vault_get by framing itself as the cheaper first-pass reader, though it never names those siblings directly.

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 this first for any question about how to do something in this vault" gives clear when-to-use guidance and positions the tool ahead of alternatives ("Cheaper and more trustworthy than reading whole notes"). What is missing is an explicit when-not / routing rule naming the sibling tools (vault_search, vault_get, vault_load_bearing) for cases this tool does not cover.

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