Merchant Discovery

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

Discloses it's a proxy (proxied to Grand Reserve), costs 3 MESH/call, and that 'the mesh never sells' — clarifying the referral-only business model. Annotations provide openWorldHint=true and destructiveHint=false but not readOnlyHint, so description's disclosure of the mesh proxy and pricing adds real value beyond structured data. Could add rate-limit or auth behavior, but the core traits are well disclosed.

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?

Single dense paragraph, front-loaded with the core value proposition, followed by concrete input/output schemas and proxy/cost info. Every sentence adds information — no filler. The inline code-style object shapes are efficient and scannable.

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 complex tool (nested objects, no output schema, proxied mesh call), the description covers the input contract, the card return shape with all fields, the proxying target, and pricing. The output shape explanation compensates for the absence of an output schema. Minor gap: no error/edge-case behavior, but reasonably complete for this complexity level.

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% (only 'input' parameter), but the schema's own description of 'input' is generic ('Capability-specific payload') and unhelpful. The tool description fills this gap by specifying the actual shape: {message: string, prefs?: object} and the return structure with cards fields. This is valuable meaning beyond the generic schema, though still somewhat thin on parameter format details.

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 clearly states it answers natural-language questions about wine/cigars/spirits and returns curated picks with live inventory, prices, ratings, and buy links. It distinguishes itself from siblings like search, fetch, and mesh_discover by framing it as an 'AI sommelier' that curates across a mesh of merchant servers. Named as 'Discovery and referral only' which clarifies its unique cap.

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 description explains what domain it applies to (alcohol products) and that it's a discovery/referral tool that deep-links to merchants' sites, not selling directly. It doesn't explicitly name alternative tools for when NOT to use it, but the domain specificity and mesh-proxy context imply clear usage. Slight gap: no explicit alternative naming, but context is adequate.

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