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

Annotations already declare read-only, open-world, and idempotent behavior. The description adds genuinely useful behavioral context: results are ranked best-first, and each result may include a connect URL, inline connection, or pull details depending on publisher-provided data. No contradiction with annotations.

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?

Three compact sentences front-load the operation, then cover query fields, ranking, optional filters, and result content without filler. Every sentence earns its place.

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 search tool with a full schema and an output schema, the description covers query scope, ordering, filters, and the shape of results. Minor operational details like limit handling and pagination are omitted, but the schema already supplies those.

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 all parameters are already documented. The description maps the optional filters to kind, domain, and trust, but adds no new semantic detail beyond the schema; it mainly frames them as optional adjustments.

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 and resource: it searches the StealthStack ARD index for agentic resources discovered across the open web. It also specifies the query mechanism (free-text over name/description/tags) and ranking, which clearly separates it from the get/list siblings even without naming them.

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 use when a free-text, ranked search is needed and notes optional filters, but it never names get_resource or list_resources or states when those alternatives are preferable. There is no explicit when-to-use versus alternative guidance.

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