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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds non-obvious behavioral context: that the reference format is auto-detected, which helps the agent understand input flexibility without additional calls. It does not describe error handling for invalid references, but the annotation coverage lowers the bar, and this added detail is valuable.

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 two sentences, front-loaded with the primary action, and provides essential format details without redundancy. Every word earns its place, and the structure is clean.

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 has an output schema and 100% schema coverage, the description needn't explain return values or every parameter. It covers the core purpose, the input format nuance (auto-detection), and the single-paragraph scope. It could mention when not to use it (e.g., for context or random access), but overall it is sufficiently complete for a simple lookup tool with strong schema and annotations.

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%, so the baseline is 3. The description adds meaning beyond the schema by naming the three formats (globalId, standardReferenceId, paperSectionParagraphId) and explicitly stating auto-detection, which clarifies how the 'ref' parameter should be interpreted. This goes beyond simply restating schema info.

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 uses a specific verb ('look up') and resource ('paragraph by reference'), clearly distinguishing it from sibling tools like paragraphs.random or paragraphs.context. The mention of 'specific paragraph' and the three reference formats leaves no doubt about what the tool does.

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 clearly states the context of use ('specific paragraph by reference') which implies it is for targeted lookup, not random or contextual retrieval. It doesn't explicitly name alternatives or exclusions, but the context is clear enough for an agent to choose this tool when a reference is available.

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