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

Annotations already mark readOnly/openWorld/idempotent, so the bar is lower. The description adds concrete behavioral detail beyond annotations: it returns a count, kind breakdown, and page of resources, and explains how connect info is represented (URL when available, otherwise inline/pull details). This gives an agent a good sense of what the call will produce.

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?

Four short sentences, each carrying distinct information: scope, filters, return shape, and sibling routing. The most identifying information (browse ARD index) is front-loaded, and there is no filler.

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?

With readOnly/openWorld/idempotent annotations and a full output schema, the tool's safety and return contract are already covered. The description adds the index scope, filtering options, the count/breakdown/page return summary, and the sibling routing, which is enough for an agent to call it correctly.

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% with detailed enum/description text for all four parameters, so the baseline is 3. The description summarizes three of the four filters (kind, domain, trust) and ties them to the browse intent, but adds little semantic detail beyond the schema; limit is left to 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 opens with a specific verb and object ('Browse the StealthStack ARD index') and names concrete resource types. The last sentence distinguishes it from search_resources ('for a specific need'), and the list-vs-get distinction with get_resource is clear from the name/title. This is a clearly scoped read/browse tool.

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?

It explicitly tells agents to use search_resources for a specific need, giving a clear branch point between browsing and searching. It mentions optional filters but does not spell out exactly when get_resource is the right choice, though the list/get contrast is implied by the sibling set.

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