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

With no annotations, the description carries the full behavioral burden. It does disclose the return shape ("matching registry rows or one lookup record, with ids and reviewed metadata"), which is genuinely useful, but it never states that the call is read-only and side-effect free, nor how limit/offset pagination behaves or what happens when a lookup finds nothing.

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?

Three short sentences, each doing distinct work: scope, intended use, exclusion, and return shape. The most decision-relevant content (what it searches and the id-discovery purpose) is front-loaded with no filler or restated title.

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 an eight-parameter, one-required discovery tool with no output schema, the description covers scope, purpose, exclusions, and the rough return shape well enough to call it correctly. The remaining gap is that applicability of filters by kind (chain_id only for feeds, verify_onchain only for RWA lookups) is left entirely to the 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 100%, so the schema already documents all eight parameters and the enum values for kind and category, making 3 the baseline. The description adds only that results may be "one lookup record" versus multiple rows, and it does not explain that filters such as chain_id, category, and is_active are kind-conditional.

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 ("Search") plus the exact resource families it covers, enumerating them (symbols, feeds, protocols, stablecoins, protocol risk parameters, RWA instruments/context, settlement-evidence packs, setup recommendations). It also names what it is not ("Do not use it to read live prices or health"), which separates it cleanly from get_oracle_price, get_oracle_health, and the prepare/verify siblings.

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?

Gives an explicit positive use case — discover the exact ids that a price, safety or execution tool expects — which routes the agent here as a first step before calling check_trade_safety or get_oracle_price. It also gives an explicit exclusion ("Do not use it to read live prices or health"), so both the when and the when-not are stated rather than inferred.

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