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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description aligns with that by stating it produces a report without selecting a winner. It adds useful context: deterministic output, returned digests, and pricing details ($0.05/call). It does not describe every internal step, but the key behavioral guarantees are transparent.

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 core action, and every phrase earns its place (inputs, outputs, key constraint, pricing). No fluff or repetition of schema details.

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?

Despite lacking an output schema, the description enumerates all major output components (union, exact duplicate IDs, field conflicts, one-sided sets, counts, digests), giving the agent a clear picture of results. It also communicates the critical constraint (no truth claim) and cost. Minor gaps: it doesn't explain 'digests' in detail, but the overall context is sufficient for a tool with this complexity.

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 input schema provides 100% coverage of parameter descriptions, including detailed constraints (patterns, enums, bounds). The description itself adds minimal parameter-specific value beyond 'buyer-supplied' and 'normalized', which are already in the schema. Baseline of 3 is appropriate since the schema does the heavy lifting.

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 ('Reconcile') and resource ('two buyer-supplied batches of normalized US brand signals'), and clearly enumerates the outputs (union, duplicate IDs, field conflicts, etc.). It distinguishes from sibling tools by emphasizing 'without choosing a winner or making a truth claim', which is unique to this merge-report tool.

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 implies when to use: when you have two normalized signal batches and need a reconciliation report. It also clarifies the non-decisive nature ('without choosing a winner'), suggesting this is for analysis rather than merging into a single authoritative set. However, it does not explicitly name alternatives or state when NOT to use it, so I deduct slightly.

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