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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds 'bounded context' and 'only the authenticated owner's private collection', which provide useful behavioral context about the data scope and result size limits. It does not contradict annotations, and the added context goes beyond what annotations state, but it does not disclose return format, pagination, or error behavior. With annotations present, a 3 is appropriate.

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 a single, tight sentence with no filler. The key verb and scope are front-loaded. It is efficient and earns its place, though it is slightly terse given the complexity of the tool.

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 retrieval tool with five parameters and an output schema, the description is under-specified. It lacks any guidance on parameter usage—e.g., how to construct a query, what collections are valid, or the meaning of limits—despite 0% schema coverage. While the output schema covers return values, the absence of parameter semantics and usage context makes it incomplete for an agent to call correctly. Annotations mitigate safety concerns but do not fill this gap.

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 the description does not mention any of the five parameters. Parameter names like query, collection_id, limit, max_hits, and max_context_chars are somewhat self-explanatory, but without any description-level guidance on their meaning, formatting, or interplay, an agent must rely on assumptions. The description does not compensate for the lack of schema documentation, so this is a significant 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 clearly states a specific verb ('Retrieve'), a resource ('context'), and a scope ('only the authenticated owner's private collection'). This distinguishes it from broader retrieval tools like search_knowledge or retrieve_context, though it does not explicitly name alternatives. The scope is precise and the purpose is unambiguous, but it could be stronger by naming the sibling it replaces.

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?

The description implies usage context: it is for the authenticated owner's private collection, so it naturally excludes queries against shared or public knowledge. However, it does not explicitly state when to prefer this tool over alternatives like retrieve_context or search_knowledge, nor does it mention any exclusions. The scope is a usage hint but not a full guideline.

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