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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. Because there is no output schema, the description's enumeration of returned metadata (prices, limits, freshness, payment rails) is genuinely useful. It still says nothing about the response shape (list vs map) or whether results reflect live state or a cached catalogue.

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 keyword "Discovery", so structure is sound. However the first sentence is a long run-on enumeration including low-level plumbing detail ("v1 and v2, exact scheme, USDC on Base and Solana") that could be compressed without losing selectability signal.

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 one-optional-param discovery tool with no output schema, the description does the important work of telling the agent what fields come back, which is otherwise unknowable. What is missing is the ordering/relationship to the sibling tools and the unfiltered default result set.

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 coverage is 100% with an explicit enum, so the schema already documents the parameter fully. The description adds the intent of the parameter – acting as a narrowing filter over an otherwise full catalogue – which is a modest semantic gain but nothing about the unfiltered default behavior beyond implication.

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?

Opens with "Discovery:" and names the concrete catalogue contents (task ids, prices, billing units, limits, sources, freshness, MCP tool names, payment rails), which clearly separates it from action siblings like deps_get_package or tenders_search. It is clear what the tool does, though the enumeration is dense enough that the core purpose takes effort to extract.

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?

"Discovery" and "Pass product ... to narrow it" imply this is the entry point before invoking the product-specific tools, but that is inference rather than statement. There is no explicit "call this first" instruction and no reference to any sibling tool, despite ~40 siblings in the namespace.

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