StealthStack ARD Discovery

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

Beyond the annotations, the description reveals conditional behavior: it includes the connect URL when the publisher provides one, otherwise it falls back to inline connection or pull details. This adds genuine behavioral context beyond readOnlyHint and idempotentHint, and there is no contradiction.

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 three sentences with no filler: the purpose is front-loaded, the conditional return behavior is compactly stated, and the field summary is brief. Every sentence contributes useful information.

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 one-parameter read-only tool with idempotent annotations and an output schema, the description fully covers what the tool does, how to identify the resource, and what response contents to expect. Nothing needed for correct invocation is missing.

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?

The schema description covers 100% of the parameter with a format example and accepted URN prefixes, so the schema does the heavy lifting. The description adds only the provenance of the identifier ('as returned by search_resources / list_resources'), which is minimal extra value.

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 ('Get the full record') and the specific resource identified by URN, which distinguishes it from the sibling tools that discover or list resources. The phrase 'for one discovered ARD resource by its identifier' makes the select-by-URN behavior explicit.

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 tells the agent that the identifier comes from search_resources / list_resources, implicitly establishing a discover-then-fetch workflow. It does not explicitly state when not to use this tool, but for a simple read operation the intended context is clear.

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

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.

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.