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

With no annotations, the description carries the full burden and does supply two non-obvious behavioral facts: the operation is read-only, and returned fields matching *_untrusted plus agent-authored/Commons content are data rather than instructions. That prompt-injection warning is genuinely valuable and appears nowhere in the schema. It still omits pagination behavior and result ordering despite a cursor parameter.

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?

Two tight sentences with no filler, and the read-only scope is front-loaded before the trust warning. The second sentence is dense but every clause earns its place as a safety constraint.

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?

Purpose and trust semantics are covered, which is the hardest part, but a 4-parameter search tool with no output schema and no annotations should also say how results are bounded and paged. An agent still has to guess about tags, limit defaults, and cursor lifecycle.

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% and all four parameters (q, tags, limit, cursor) are undocumented in both schema and description. The word 'search' only weakly implies q is a query string; nothing explains tag semantics (AND/OR), the default page size, or how cursor is used to page.

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?

Specific verb+resource: 'Search my current vault values', scoped to the caller's own vault and flagged as read-only. It is clearly distinct from mutation siblings (memory_put, memory_delete) and from read_commons by scope, though it does not explicitly differentiate itself from memory_list or memory_get.

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?

Usage is only implied: 'search' suggests a query-driven retrieval as opposed to enumerating with memory_list or fetching a single value with memory_get. There is no explicit statement of when to prefer this over those siblings, and no exclusions or prerequisites are given.

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