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

The description adds valuable behavioral details beyond the annotations, such as the possible return states (confirmed, weakened, unresolved, new_claim) and the guarantee that it won't invent evidence. This goes beyond the readOnly/idempotent hints already provided.

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 three concise sentences covering purpose, parameters, and behavior, with no redundant or irrelevant information. It is front-loaded with the core purpose.

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 14-parameter tool with full schema descriptions, the description covers the core usage scenario and return categories. It doesn't elaborate on every optional filter, but the schema handles those details, and an output schema exists, so return structure isn't needed.

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?

The description highlights the relationship between parameters (claim_text or query, plus river_tripcode or issuer), which is not obvious from the individual schema descriptions. This provides logical grouping that aids correct invocation.

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 compares a claim to River claim records and evidence refs, using a specific verb ('compare') and resource. It doesn't explicitly differentiate from sibling tools like deltasignal_compare_article_to_filing_evidence, but the claim-based focus is distinct.

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 gives direct usage guidance ('pass claim_text or query plus river_tripcode or issuer') and notes the tool is read-only, but it doesn't mention alternatives or when-not-to-use scenarios, which would help distinguish from similar search/compare tools.

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