directory_summaryRead-only. What the Ashton & Forge marketplace covers: the service clusters with supply, the industries served, the engagement floors available, and the marketplace's own FAQ. Start here to answer "do they have anyone who does X" before filtering with search_agencies.
Returns coverage, not a headcount. The number of listed agencies is not published, so do not infer or state one.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are empty, so the description carries full behavioral burden. It opens with 'Read-only', explicitly disclaims headcount data, and warns against stating an unprovided number. This goes well beyond the schema and gives the agent important non-obvious behavior.
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 tight sentences: a scope statement, a routing/usage instruction, and a critical limitation. Every sentence earns its place, and the most important behavioral facts ('Read-only', 'Start here') are front-loaded.
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 parameterless read-only directory overview with no output schema, the description is complete: it says what content is covered, when to use it, which sibling to use afterward, and what not to infer. No essential operational detail 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 tool has zero parameters, so there is no parameter semantics to clarify. The description still adds value by explaining what kind of content is returned, which is the only meaningful semantic dimension for a no-input tool. This meets the baseline for zero-parameter tools.
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, scoped purpose: it describes what the Ashton & Forge marketplace covers, enumerating content (service clusters, industries, engagement floors, FAQ). It also explicitly frames its use case ('do they have anyone who does X') and distinguishes itself from search_agencies, making sibling differentiation clear.
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 when-to-use guidance: start here for coverage questions before filtering with search_agencies. It also provides a clear do-not-do constraint: 'Returns coverage, not a headcount' and warns against inferring a number of listed agencies.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct role: summary provides high-level coverage, search filters actual listings, and get_matched explains the matching process. The only potential confusion is between summary and search when answering 'do they have X', but the descriptions clearly direct users to start with summary before searching.
Tool names mix conventions: directory_summary is noun-noun, get_matched is verb + past participle, and search_agencies is verb + noun. There is no consistent verb-object pattern, though the names are still readable in context.
Three tools is well-scoped for a read-only directory/marketplace server. Each tool earns its place and there is no redundancy or overwhelming surface area.
The set covers the full buyer workflow: understand marketplace coverage, search for matching agencies, and learn how to get matched. Search with no filters returns the whole directory, and get_matched provides the only necessary route to engage, so there are no dead ends.