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

Goes well beyond the readOnly/idempotent annotations: it promises that unknown, stale, or conflicting data stays explicit, that an unknown price is never treated as zero, and that costs need full assumptions. It also discloses pagination strategy (repeat the call with `view` on large results) and a 409 restart condition, which annotations cannot express. Slightly reduced because 'one call per POST' is cryptic and the read-only claim sits oddly beside POST framing.

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?

Front-loaded with what is compared, then behavior, then data-quality rules, then operational rules – dense and largely waste-free. A few telegraphic fragments ('Costs require all assumptions', 'one call per POST') trade clarity for brevity.

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 high-complexity 9-parameter comparator, the description covers paging, conflict recovery, missing-data policy, cost preconditions, and access scope, and an output schema exists so return values need no explanation. The remaining gap is parameter-level semantics for the priority/scenario machinery, which the description leaves entirely to an undocumented schema.

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% across 9 parameters, so the description must carry the semantics and it only partially does: it constrains solution_ids to 2–3, implies requirements/criteria/context, ties cost_scenario to 'all assumptions', and points at `view` for large results. It says nothing about `priority`, `priority_required`, `locale`, the criteria-vs-requirements distinction, or the many required Scenario fields (users, currency, tax_basis, horizon_months, billing_periods, allow_current_price_projection).

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?

Names a specific verb and resource and quantifies scope ('Compare 2–3 catalogue IDs') plus the comparison axes (capabilities, offer, context, dated sources). It does not name or differentiate against siblings such as find_comparable_solutions or search_solutions, so an agent must infer that this is the deep multi-ID comparator rather than the discovery 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?

Indirect usage guidance is present: IDs must be discovered elsewhere (/api/capabilities, /api/solutions/{id}/specification), and cost comparison requires all scenario assumptions. However it never states when to choose this over find_comparable_solutions, search_solutions, or get_solution, and gives no exclusions.

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