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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety and scope profile is covered. The description adds one genuine behavioral rule ('cohorts counted once per side'), which tells the agent results are deduplicated per side. It says nothing about result volume, ordering, or what happens when no contradictions exist, leaving those to the output schema.

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?

Two short sentences, zero filler. The core purpose is front-loaded with caps for emphasis and the follow-up action is deferred to the end where it belongs.

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?

With an output schema present, return-value detail is unnecessary, and read-only behavior is covered by annotations. What remains thin is the meaning of the optional track filter and whether an empty result is expected in a sparse ledger.

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 single 'track' parameter has 100% schema description coverage ('A, B, C, D, E or unassigned'), so the schema carries the semantics. The description never mentions track or explains when to leave it unassigned, so 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?

States a specific verb ('FIND DISAGREEMENTS') and a specific resource ('the T1D evidence ledger'), then narrows the unit of analysis to 'outcomes, trials or papers with both supporting and contradicting claims'. That is clearly distinguishable from siblings like search_cure_evidence or get_open_questions without opening any schema.

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 'NEXT: trace_scientific_claim on either side' clause gives a useful follow-up path, which implies this is a scouting/triage step. But it never says when to choose this over alternatives such as search_cure_evidence or claim-level tools, nor any precondition (e.g. whether the ledger must be populated first).

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