Prime Vault Context

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

Annotations already indicate read-only, idempotent, and non-destructive. The description adds crucial behavioral context: priority ordering (authoritative first, then recency), token budget calculation (max_tokens * safety_factor), cap_behavior semantics ('best_effort' vs 'strict'), per-session caching via session_token, and per-document truncation. This goes beyond annotations and gives the agent a realistic model of tool behavior.

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?

The description is well-structured: a one-sentence summary, a comparison to vault_inject, a usage note, and a compact Args block. Every sentence provides necessary information, and the parameter list is essential given the lack of schema descriptions. It is appropriately sized and front-loaded.

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 tool with six parameters, no schema descriptions, and a complex token-budget behavior, the description covers all essential aspects: purpose, ordering, usage timing, parameter semantics, and edge-case behavior (cap_behavior). An output schema exists, so return-value details are not needed. The description is sufficient for correct invocation and selection.

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 descriptions are completely absent (0% coverage), so the description carries the full burden. It compensates thoroughly by defining each parameter: vault_name, max_tokens, cap_behavior, session_token, max_single_doc_tokens, and safety_factor (including default). This adds meaning far beyond the bare schema types.

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?

States a specific verb and resource: 'Pre-load all vault documents into the current session by priority order.' It clearly distinguishes from vault_inject by specifying it's equivalent to vault_inject with no query and by noting the ordering logic. This makes it easy to differentiate from siblings like vault_inject and vault_search.

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 says 'Use at session start to orient yourself on all knowledge available in a vault.' It also frames the tool in relation to vault_inject, giving an alternative reference point. This provides clear when-to-use guidance and a comparison to a sibling tool.

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