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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine behavioral context beyond them: the tool fails with an error if either underlying list changed after preparation, which signals a staleness/consistency guard an agent must anticipate and handle.

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 sentences, verb-first, with the returned content enumerated up front and the failure condition immediately after. No filler, no restatement of the title, and every clause carries information the agent needs.

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 single-parameter read-only tool with no output schema, describing the returned payload (pairs, alternatives, conflicts, missing values) and the error condition covers most of what an agent needs. The remaining gap is practical rather than structural: no guidance on how to source the comparison_id or on result size.

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 0% for the single comparison_id parameter, so the schema contributes nothing but a minLength constraint. The description implies comparisons are "prepared" beforehand, hinting at where an id originates, but never states how to obtain one (e.g., from prepare_reconciliation or list_reconciliations); the self-explanatory name keeps this at minimum viable rather than inadequate.

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 gives a specific verb ("Reads") plus the resource (a comparison) and enumerates exactly what content comes back: proposed pairs, alternatives, conflicts, missing values. That is far more precise than the title "Read a comparison" and separates it from mutation siblings like prepare_reconciliation and apply_reconciliation. It does not, however, distinguish itself from close read siblings such as get_reconciliation_fields or get_reconciled_input.

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?

Usage is only implied: the second sentence reveals a precondition (the comparison must already have been prepared and its lists must be unchanged), which tells the agent this is a post-preparation read. There is no explicit statement of when to prefer this over get_reconciliation_fields / get_reconciled_input / list_reconciliations, and no stated exclusions.

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