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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description goes well beyond this by revealing key behaviors: answers are extracted verbatim and never generated, responses always carry the source URL, and confident=false is returned with suggested readings in ambiguous or unsupported cases. This is rich, non-obvious behavioral disclosure.

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 four sentences, each carrying substantive information: core function, output behavior, fallback behavior, and language guidance. It is front-loaded with the primary purpose and avoids redundancy or filler. Every sentence earns its place.

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?

Given the tool's simplicity (two parameters, one required) and existing annotations, the description covers all critical aspects: purpose, behavior, edge cases (confident=false), ambiguity resolution (MSO), and language support. An output schema exists, so return format documentation is handled elsewhere, and the description complements it with usage context.

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 coverage is 100%, so the baseline is 3. The description adds semantic value beyond the schema by explaining language handling: 'Ask in the language you want answered — Russian and English are both first-class.' It also clarifies the special meaning of 'MSO' in context, which helps disambiguate parameter usage even though it's not directly tied to a parameter. This justifies one point above baseline.

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 the tool's function: 'Answer a question by quoting a published wiki article.' It specifies the output behavior (verbatim extraction, URL included) and distinguishes itself from the sibling 'search' tool by emphasizing that answers are never generated, only quoted. This is a specific verb+resource with clear scope.

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 provides context on when to use the tool: it handles questions answered by quotes, returns confident=false with suggested reading when coverage is lacking or context conflicts, and supports multiple languages. However, it does not explicitly contrast with the sibling tool 'search' or state when not to use it, so it falls slightly short of fully explicit guidance.

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