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

The description adds important behavior beyond the readOnlyHint annotation: it states that the tool 'parses place and varietal from the query', that it 'never fabricates' results, and that it returns an honest empty list. These are critical for agent decision-making.

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?

The description is concise with four sentences, each serving a purpose: defining the action, noting intended use cases, explaining behavior, and linking to a sibling tool. No fluff.

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 tool with one parameter and no output schema, the description is comprehensive. It covers purpose, usage guidance, behavioral transparency, and parameter semantics. It also references the sibling tool 'fetch' for completeness.

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?

Although the schema covers 100% of parameters, the description adds meaningful context: it explains how the query is interpreted (tool extracts place and varietal), and provides an example. This goes beyond the schema's dry description and helps the agent format queries correctly.

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 searches a local honey directory by free-text query and returns matching producers. It specifies the target resource (Melvea local honey directory) and the action (search and return results). It distinguishes from sibling 'fetch' by noting that fetch retrieves full detail.

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 says to use it for 'any local-honey discovery query that names or implies a place' and that it 'returns an honest empty list when nothing matches — never fabricate.' While it doesn't explicitly exclude other use cases, it provides clear context and mentions pairing with fetch, indicating appropriate usage.

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