Search Leviathan Systems articles and services; read public documents and company scope.
Scored across 3 tools
Each tool has a clearly distinct purpose: read_company_profile reads a fixed company identity, read_resource reads a specific resource by catalog ID, and search_resources discovers resources. The descriptions make the boundaries explicit, so an agent can easily select the right tool.
All tool names use consistent snake_case and follow a verb_noun pattern (read_company_profile, read_resource, search_resources). The naming is predictable and immediately understandable.
Three tools is minimal but well-scoped for a read-only public content server. Search and read cover the core workflows, though the surface is slightly thin compared to a fuller content API.
The set covers discovery (search_resources), direct retrieval (read_resource), and company profile reading, which is complete for a public read-only domain. Minor gaps exist, such as no explicit listing of all resources without a query or full-text search beyond title matching.
Read Leviathan Systems' public company identity, physical service scope, exclusions and contact guidance. Select a smaller view when only services or scope boundaries are needed.
| Name | Required | Description | Default |
|---|---|---|---|
| view | No | Return the full public profile (default), service listings, or responsibility boundaries. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds only that the content is public profile material with defined sub-views; it says nothing about auth requirements, payload size, or freshness. Adequate, but not much value beyond the 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?
Two tight sentences, front-loaded with what is returned and followed by the view-selection hint. Nothing is redundant with the title or schema and 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?
For a single-optional-parameter, read-only, closed-world tool with no output schema, the description covers the content domain (identity, scope, exclusions, contacts) and the view tradeoff, which is enough to invoke it correctly. It stops short of describing the response shape, which matters slightly more given there is no output schema.
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 enum values are already documented, so the baseline is 3. The description adds a genuine selection heuristic — prefer the smaller 'services' or 'boundaries' view when the full profile is not needed — which tells the agent why to pick a non-default value, not just what the values are.
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 gives a specific verb ('Read') and a precisely scoped resource (Leviathan Systems' public company identity, service scope, exclusions, contact guidance), so an agent immediately knows what content this returns. It does not explicitly contrast itself with the generic siblings read_resource/search_resources, which is the only thing keeping it from a 5.
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?
'Select a smaller view when only services or scope boundaries are needed' gives real guidance on parameter choice, but there is no statement of when to use this tool instead of the sibling read_resource or search_resources. Usage is implied by the content, not by explicit when/when-not framing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read a resource returned by search_resources. Returns native Markdown when available, or the canonical HTML link for preserved legacy articles. Accepts catalog IDs, never arbitrary URLs or file paths.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Exact published catalog ID, for example service:rack-and-stack. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive, and non-open-world behavior. The description adds valuable behavioral context by specifying the return format (native Markdown when available, otherwise canonical HTML link) and the accepted input category, which goes beyond the safety 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?
The description is three compact sentences with the core operation front-loaded, followed by return behavior and input constraint. No sentence is redundant.
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 simple one-parameter read tool with no output schema, the description covers how to obtain valid IDs, what the tool returns, and what inputs are invalid. Annotations cover the safety profile, so nothing essential 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 schema already documents the single id parameter with pattern and example. The description adds the meaningful constraint that only catalog IDs are accepted and never arbitrary URLs or file paths, which is not fully expressible from the schema alone.
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 states a specific verb and resource ('Read a resource returned by search_resources') and immediately distinguishes this tool from its search sibling by tying it to IDs produced there rather than to arbitrary browsing. It also clarifies the return shape, so an agent can identify the operation 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?
It clearly routes the agent to use this after search_resources and explicitly rejects arbitrary URLs or file paths. It does not compare against read_company_profile, but the intended usage context is otherwise clear and constrained.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find published article titles and physical service listings. Matches every query word in the title. Follow next_cursor with the same query and kind to read more.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Words to match in published titles; every word must match. | |
| kind | No | Restrict the catalog to educational articles or physical services. | |
| limit | No | Maximum records in this page, from 1 to 50; default 20. | |
| cursor | No | An opaque next_cursor from the same query and content revision. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: matching is conjunctive over title words only, and cursors are only valid with the same query/kind and content revision.
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 short sentences, no filler: what it searches, how matching works, how to page. The scope statement is front-loaded ahead of the mechanics.
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 zero-required-parameter search with full schema coverage and no output schema, the description covers scope, match semantics and continuation well. It omits result ordering and what fields each result carries (e.g. an id to feed read_resource), which an agent assembling a follow-up call would want.
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 four parameters are already documented in the schema, including the enum values and the 1-50 limit. The description's word-matching sentence largely restates the 'q' schema description, adding no new syntax or format detail. 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 concrete verb ('Find') and a well-scoped resource ('published article titles and physical service listings'), which separates it from the retrieval-by-id sibling read_resource. It never names the siblings, so the differentiation is inferable rather than 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?
Gives real guidance for the pagination case ('Follow next_cursor with the same query and kind to read more'), but says nothing about when to search versus when to call read_resource or read_company_profile directly, so the routing decision is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
read_company_profileread_resourcesearch_resourcesSearch and read Lynta's public documentation.
Search and read Protoperfect Labs research, documentation and glossary. Read-only.
Search and read published Quantlix services, company information and insights.
Search and fetch AgendaForge public documentation and marketing content. No authentication needed.
Add one secure layer between your agents and this server.
