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

Annotations only cover the safety profile (readOnly, non-destructive, closed-world); the description goes well beyond by disclosing grounding behavior, the confidence/blocked sentinel semantics, that sources are returned, and crucially that returned content is data rather than instructions — directly relevant to prompt-injection handling for an agent. This is material behavioural context the annotations cannot carry.

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 compact sentences, front-loaded with what the tool returns before the usage rule and the data-not-instructions caveat. No sentence is redundant with the schema or annotations.

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?

An output schema exists, so return values need not be enumerated, yet the description still surfaces the two fields an agent must act on (confidence, blocked) plus the trust boundary around document text. Nothing an agent needs to call and interpret this tool correctly is missing.

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 100%: both 'question' (plain language, 1-4000 chars) and 'conversation_history' (oldest first, last six used) are documented in the schema. The description adds no parameter-level detail, so the baseline 3 applies.

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 ('Ask') + resource ('Dibri', an org-document answering service) plus the exact response shape it produces: answer, sources, 0-100 confidence, blocked sentinel. The scope restriction ('drawn only from the organization's approved documents') further pins down what kind of answer to expect. No siblings exist, but the definition is self-distinguishing from generic answering.

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?

Gives an explicit when-to-use domain ('product, policy, pricing and procedure questions') and an explicit alternative ('instead of answering from memory'). It lacks a when-not statement (e.g. current-events or non-document topics), so it stops short of full routing guidance, but the context is unambiguous.

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