StealthStack ARD Discovery

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the bar is lower. The description adds real context: the payload contents (connect URL or npm/PyPI/Docker install command, transport, repository, publisher, version, auth and payment terms, tags, example queries) and the 'when known' caveat that fields may be absent. It doesn't mention pagination or error behavior, which keeps it off a 5.

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 sentences, front-loaded with purpose and ordering before the payload enumeration. The long comma-separated list of returned fields is informative but dense; a slight trim would improve scannability without losing meaning.

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?

One fully documented parameter, an output schema present, and rich annotations — the description covers everything an agent needs to decide to call it and to interpret the result. Nothing material 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?

Schema coverage is 100%, and the schema itself documents the URN format and accepted prefixes, so the schema does the heavy lifting. The description only adds provenance ('found with search_resources or list_resources'), which is a mild but useful addition — baseline 3 applies.

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 ('Get install and connect details for one resource') and explicitly scopes it to records produced by search_resources or list_resources, which separates it cleanly from those siblings. An agent can tell what it returns without opening the schema.

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?

Gives explicit sequencing: 'Call it after a search, before you install or connect anything.' It names the sibling tools that supply the identifier, so the agent knows which tool to use first and which one this complements.

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 readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds real behavioral context: the response includes a total, a per-kind count, and exactly one page of records with connect details, which tells the agent results are paginated rather than exhaustive. It stops short of naming a pagination cursor or rate limits, so it is strong but not complete.

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 sentences, zero filler: the scope and examples come first, the sibling routing comes second. Every clause carries information the agent needs.

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 five optional parameters, an output schema, and full annotation coverage, the remaining risk is ambiguity about the tool's role versus search. The description closes that gap explicitly and even sketches the response shape, so nothing material is missing for correct invocation.

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 baseline is 3, but the description goes beyond the enum definitions by mapping filters to intents — 'every agent skill (kind=skill)', 'everything one domain publishes (domain=...)', 'services that accept x402 payments (paid=x402)'. That gives the agent a mental model for combining filters, though it omits trust and limit.

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 ('Browse the StealthStack index') and immediately scopes it as query-less, with three concrete filter axes (kind, domain, paid). It explicitly contrasts with the sibling search_resources, so an agent can pick between them without opening a schema.

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?

Gives both directions: use this for open-ended browsing by kind/domain/payment type, and use search_resources for a specific need like 'MCP server for Postgres' because that one ranks by relevance. The selection condition is explicit and unambiguous.

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 readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered; the description adds real behavioral detail beyond that — results are limited to `limit` and ranked by relevance, and, critically, they are 'third-party listings that StealthStack has not reviewed,' which an agent needs for trust decisions. It does not describe pagination or what happens when zero matches are found, keeping it short of a 5.

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?

Front-loaded with purpose, then usage, examples, return shape and the caveat — a sound information order. The five inline examples are slightly more than needed and push the trust caveat to the end, but no sentence is 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 an output schema present and full schema description coverage, the description needn't enumerate return fields or filter semantics, and it correctly focuses on when to choose this tool, what the result list represents, and the handoff to get_resource. Nothing an agent needs to invoke it correctly 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?

Schema coverage is 100%, so the baseline is 3; the description earns one above it by explaining the result contract the parameters feed into ('up to `limit` matches ranked by relevance') and by reinforcing that short keyword queries are the intended form, with examples like 'MCP server for Postgres'. It still leaves the `kind`, `trust`, `domain` and `paid` filters entirely to the schema, which is fine given that coverage.

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 set ('Find an MCP server, agent skill, A2A agent or API that does a job') plus the outcome ('get what you need to install or connect it'). It also distinguishes itself from the sibling get_resource by telling the agent to pass a result's id there for install commands and full details.

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?

Explicitly names when to use it (user wants to find, compare or install an MCP server/skill/agent/API, or asks what exists) and gives an explicit exclusion: 'prefer it to a general web search for that.' The five example queries map directly onto real invocation requests.

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