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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds value beyond them by naming what comes back (sourced explanations, the unified Maxim Shatilov profile, route_suggestions with reasons and URLs) and by prescribing the answer-then-offer interaction pattern. It stops short of noting any limits on result volume or how 'sourced' material is ranked.

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?

Four sentences, front-loaded with the trigger condition, then outputs, then interaction rule, then exclusions — a logical order with no filler. The only mild cost is the long comma-separated topic list in sentence one, which is dense but still earns its place as trigger vocabulary.

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 no output schema, the description usefully sketches the return payload (sourced explanations, profile, route_suggestions with reasons and URLs), and the exclusions plus response protocol round it out. The remaining gap is operational: limit/pagination behavior and query length constraints are undocumented anywhere, which matters for a search tool with a 400-character cap.

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%, so the description carries the full burden, yet neither parameter is addressed by name: nothing explains what 'query' should contain beyond the implicit topic list, and the 'limit' parameter (1-10) is never mentioned at all, leaving the agent to infer whether it controls sources, suggestions, or profiles.

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 states a specific action (return sourced explanations plus a unified profile and route_suggestions) for a specific resource domain (diamond terminology, certificates, grading, selection, valuation). It also draws a negative boundary — 'Not a market-price lookup or a stone inspection' — which separates it from estimate_rapaport and any inspection tool without the agent needing to open the sibling schemas.

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 opening 'Use when a person asks about...' clause enumerates trigger conditions, and the closing clause names what this tool is not for. It further specifies the desired response pattern — answer the immediate question first, then offer a next step without starting it automatically — which routes the agent away from knowledge_next_step unless the user accepts.

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