vault_list

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds real behavior beyond that: trailing '/' on directory names, omission of protected/symlink entries, and a failure mode where overflow errors rather than truncates. That error-over-truncation guarantee is exactly the kind of context an agent needs and could not get from the annotations.

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?

A single tight sentence pair: the core action and root-addressing rule come first, then the behavioral caveats. No filler, no repetition of the schema, and the most decision-relevant constraint (root path) is 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?

With an output schema present, return-shape explanation is unnecessary, and the annotations carry the safety profile. The description adds the filtering rules and the error-not-truncation contract, which is most of what an agent needs; only the maxEntries semantics remain undocumented in prose.

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 0%, so the description has to carry both parameters. It explains path well (omitting it or passing "" selects root), and 'overflow errors, never truncation' indirectly implies maxEntries caps results and errors when exceeded, but maxEntries is never named or bounded in prose. Partial compensation for a coverage gap, hence a mid score.

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 gives a specific verb+resource ('List a Vault directory') and immediately pins down the scope ('omit path or use "" for root'), which is enough for an agent to distinguish it from vault_read, vault_get_document_map, and search_query without opening a schema. It stops short of naming a sibling alternative explicitly, so it falls just below the top mark.

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?

It tells the agent how to address the root directory ('omit path or use ""'), which is useful invocation guidance, but it never states when to choose vault_list over search_query or tag_list, nor any exclusions or prerequisites. Usage is implied by the name rather than argued.

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