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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds real context by disclosing that the registry is public and that returned recipes are pre-vetted (fixture, terms review, health count). It stops short of describing result size, pagination, or ordering, which matter for a registry-wide search.

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 tight sentences with no filler; the resource identification comes first and the empty-query behavior is placed last where it acts as a usage note. Nothing is redundant with the title or schema.

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 two-parameter, read-only, open-world search with no output schema, the description covers what the tool searches and what the results guarantee. The remaining gap is operational detail such as result limits or ordering, which is minor given the annotations.

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%, so the field-level matching rules (id, name, description, tags, host) and the schema filter are already documented. The description still contributes beyond the schema by stating that an empty query returns everything, which clarifies the zero-required-parameter behavior.

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) and resource (recipes in the public gleanyard source registry), and defines what a recipe is: a source that already works, with a fixture, a terms review and a health count. It does not explicitly contrast with the similarly named search_records sibling, leaving that distinction to inference.

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 clause 'Empty query lists all' gives one concrete usage mode (browse the full registry), which implies the tool can be used for both lookup and enumeration. There is no guidance on when to use this versus get_recipe or search_records, and no stated prerequisites or result-count limits.

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