search_vendors

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

Annotations already declare readOnlyHint=true, covering safety. The description adds the typeahead behavior and the category scoping, which are not present in annotations. This provides useful context about how the search operates (partial-name matching, category filtering) without repeating the read-only fact. It does not mention response format or limits, but the annotation lightens the burden.

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 a single sentence with zero filler. It front-loads the core action ('Search for vendors by name') and immediately adds the typeahead and category qualifiers. Every word earns its place, making it highly efficient for an agent to parse quickly.

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 simple, read-only search tool with two parameters (one required) and no output schema, the description is adequate. It covers the essential behavior (search by name within a category) and the typeahead aspect. It does not explicitly state that it returns a list of matching vendors, but that is a natural inference for a search tool, and the schema handles parameter details. The annotations cover safety, so the description meets the needs without over-explaining.

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 description coverage is 100%, so both query and taxonomy_key are already documented in the schema. The tool description restates the query as 'by name (typeahead)' and taxonomy_key as 'within a vendor category', adding a slight behavioral nuance (typeahead) but not significant new meaning. With full schema coverage, a baseline of 3 is appropriate; the description adds marginal value beyond the schema.

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 the action (search), the resource (vendors), and the specific behavior (typeahead by name) plus a scoping constraint (within a vendor category). It distinguishes itself from sibling tools like list_vendors, add_vendor, etc., by emphasizing the name-based typeahead search, so an agent can immediately identify when this tool is relevant.

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 implies usage (searching vendors by name) but does not explicitly state when to choose this over alternatives such as list_vendors (which presumably returns all vendors) or search_registry_products. There is no mention of use cases like pre-filling a form or filtering a dropdown, and no exclusions or comparisons are provided. The guidance is implicit rather than explicit.

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