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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false. The description adds value beyond them by disclosing what comes back ("sourced, dated summaries" — provenance and recency) and the advisory boundary ("information, not advice"). It omits practical traits like default result count, the 25-result cap, and any paging behavior.

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, front-loaded with the verb and resource, then the filter axes and the return/disclaimer note. The long parenthetical enumerations are dense but every item corresponds to a real filter, so the length is functional rather than padding.

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?

No output schema exists, so the description usefully characterizes the return as sourced and dated summaries. For a 10-parameter read-only search tool with strong annotation coverage and 70% schema descriptions, this is close to sufficient; only result-cap/limit behavior and the language parameter are left unexplained.

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?

With 70% schema coverage across 10 parameters, the description meaningfully maps description-level vocabulary onto parameters: the capability enumeration ("place orders, draft orders, read only, none") matches the capability enum exactly, and "Spain availability/licence" covers both Spain booleans. It leaves lang, limit and official_only unaddressed, which is the remaining gap.

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 and resource ("Find providers in the AgentBroker Index") and immediately enumerates the dimensions searched: name, type, agent capability, assistant, tradable asset, and Spain availability/licence. An agent can tell this is the broad lookup/list tool rather than the comparison or single-record 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?

Usage is implied by the enumerated filter axes and the closing "Read-only; information, not advice," giving a clear sense of the legitimate context. However, it never names alternatives such as compare_providers or get_provider, nor states when-not to use it (e.g. for a single known provider or for head-to-head comparison).

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